AI Security Blogs

Vulnerabilities used to move at human speed. A researcher found one, disclosed it, and defenders had days - sometimes weeks - to respond before it was weaponized in the wild.

That window is gone. According to the Edgescan 2026 Vulnerability Statistics Report, it still takes an average of 55 days to fix a vulnerability - but the Zero Day Clock shows attackers going from disclosure to first exploit in as little as 6 hours. And per the 2025 DORA Report, once a fix is written, it can still take more than a week to get from commit to production. Security teams are trying to close a gap measured in hours with a process measured in weeks.

Frontier models like Claude Mythos are pulling on both ends of that gap at once. On one side, they're giving attackers a faster way to find and chain vulnerabilities. On the other, they're giving defenders a faster way to find vulnerabilities too. Point an LLM scanner at a codebase and it will surface far more findings than traditional tools ever did. Project Glasswing partners saw roughly 10x more vulnerabilities surfaced during testing. That's a good thing only for visibility. But it creates an operationalization challenge. Without any normalization, deduplication, reachability or integration with developer workflow, it just creates more backlog for a remediation process that was already too slow. Comcast, a Project Glasswing participant, put a number on that gap in its own testing: 44% of critical- and high-severity findings turned out to be false positives.

Security has to move at machine speed now, end to end: scan without drowning in noise or cost, triage what's actually worth fixing, remediate it, get the fix into production before the window closes, and still protect the perimeter while the fix is fully deployed. That's what this launch is about.

Scan without the guesswork: AI SAST and LLM Scan Orchestration

Everything downstream starts with the scan, so that's where machine speed has to start too.

LLM-based scanners are genuinely good at finding things traditional static analysis misses, which is exactly why they've generated so much attention. But they're still probabilistic: point the same model at the same code twice and you can get different findings, different false positives, latency that can hold up pipelines, and a token bill that scales with every file you scan. That's a real cost, and it makes it unrealistic to scan continuously in CI/CD. 

That’s why Harness is embracing the hybrid approach - use LLMs for one-off hunting scans, and a deterministic SAST augmented by AI in the pipeline.

AI SAST 

Harness pairs a high-recall dataflow engine with an AI confidence layer that classifies each finding as confirmed risk, potential risk, or contextually safe. It's deterministic where LLM scanning is probabilistic: same code, same result, every time, with a traceable path from input to sink. In our own benchmarking against the OWASP Java corpus, that confidence layer cut false positives by 79% (from 454 down to 95) and lifted precision from 74% to 93%, while preserving 91% recall - almost no loss of signal for a large gain in precision. It also extends into broken access control (IDOR), a class dataflow analysis alone can't see because there's no malformed input to pattern-match, only a missing authorization check: 71% recall at 99% precision across a 390-case corpus spanning Go, Java, and Python.

LLM Scan Orchestration 

For teams that want to run LLM-based scanners, Harness now orchestrates them natively inside the CI/CD pipeline, reducing token spend, increasing scan speed, and feeding results into the same triage and remediation workflow as everything else - instead of a separate spreadsheet living outside your pipeline.

Which should you choose? AI SAST reduced the triage queue by 21% in our benchmark (1,746 flagged cases down to 1,381 actionable ones) without giving up coverage, and without paying a per-scan LLM bill to get there. LLM scanners still have a place, and Harness will keep making them faster and cheaper to run. But when the choice is between a probabilistic result and a deterministic one at comparable or better accuracy, the deterministic one should usually win by default.

From finding to fix: Triage Agent and Remediation Agent

A scanner - any scanner - is only useful if what it finds actually gets fixed. And the steady output of SAST and SCA scanning has a particular shape: a high volume of findings that need to be sorted by real risk before anyone starts fixing, because most security teams already have more open findings than they can act on in a sprint, let alone a day. And most of that backlog isn't as urgent as it looks: in the same Project Glasswing testing, only 36% of critical-severity and 33% of high-severity findings were confirmed exploitable. Sorting through that backlog by hand, then writing and validating each fix one by one, is exactly the kind of toil that doesn't scale with the volume scanning produces, so Harness is introducing an agentic workflow that does.

Triage Agent 

Harness’s Triage Agent prioritizes what's actually exploitable, combining CVSS, EPSS, and reachability analysis to cut a sprawling SAST/SCA finding list down to a clean, actionable backlog - so your team works on real risk, not everything with a CVE number.

Remediation Agent 

Once a finding is prioritized, the Remediation Agent applies the fix and validates it in your pipeline to prevent breaking builds, then opens a human-reviewed pull request. Developers stay in charge of what merges; the agent just does the work of getting them a validated fix instead of a bare finding.

Function-level reachability 

Reachability analysis doesn't stop at "is this vulnerable package called." Harness now traces the call path down to the specific vulnerable function, so a dependency only gets flagged if that exact function is reachable in your code. Both agents work off that sharper signal: fewer false positives for Triage Agent, and a precise code path to close for Remediation Agent.

Because these agents run on top of Harness's existing pipeline governance (policy gates, approvals, chain of custody), a fix doesn't just get written faster, it gets safely into production faster too. That's the piece that's easy to overlook: a fix sitting in a pull request isn't protection. A fix that's deployed with an audit trail through the same governed pipeline you already trust - that's protection.

Zero-days don't wait in line: Zero-Day Agent

Everything above assumes there's time to scan, triage, and prioritize before anyone acts. A zero-day doesn't give you that time. The clock starts the moment it's disclosed, and most of that time doesn't get spent writing a fix - it gets spent figuring out if you're even affected and waiting for a fixed artifact to work its way back through build, test, and deploy.

A newly disclosed zero-day doesn't need to wait in a triage queue behind the rest of the backlog; it needs an immediate, end-to-end response. Zero-Day Agent runs that response itself: it continuously monitors for newly disclosed zero-day vulnerabilities, automatically identifies every affected artifact and pipeline across your environment, and takes it the rest of the way - applying and validating a fix, then opening a human-reviewed pull request. No separate triage step, no handoff to another agent. Blast radius mapping that used to take days happens in seconds, and a fix is ready for review shortly after.

Shielding production while the fix is in flight

Even with agents compressing the fix cycle to hours, hours are still a window. Harness closes that window from the other direction with virtual patching: when API testing discovers a vulnerability, it can create a virtual patch and deploy it on our WAAP - no tickets or code changes required. Production is shielded within minutes of discovery, while the permanent fix is worked in code. When the fix ships, the virtual patch comes down.

That's the same principle running through this whole launch: don't wait for the slowest step in the chain to gate every other step. Contain the risk immediately, fix it in parallel, and let each part of the system move as fast as it's capable of moving.

Security at machine speed

None of this works as a single point tool. The value comes from AI SAST, LLM scan orchestration, Triage Agent, Remediation Agent, Zero-Day Agent, and virtual patching all sitting on the same platform - the same one that's already deploying your code, governing your pipelines, and holding chain of custody on every artifact. Finding a vulnerability faster only matters if fixing it and deploying it are just as fast.

The organizations that build this operating rhythm now, those that scan without noise, triage in minutes, ship a validated fix in hours, shield production the whole time, will be the ones still moving confidently when attackers have the same frontier models defenders do. The ones that don't will keep measuring their response time in weeks while the threat measures its head start in hours.

Want to learn more?

Read about Harness's perspective on how Mythos is not just a security problem, but also an engineering problem. To learn more about the security capabilities in this launch, request a demo or reach out to your Harness account rep.

Harness AI Security provides a unified control plane for AI discovery, risk visibility, and runtime protection, helping organizations operationalize key requirements of the EU AI Act. Instead of relying on manual audits or fragmented tooling, teams get continuous insight into how AI systems are built, exposed, and used, along with the evidence needed to demonstrate compliance.

By combining AI asset discovery, risk classification, data flow visibility, and runtime enforcement, Harness enables customers to proactively identify high-risk systems, prevent unsafe integrations, and continuously monitor AI behavior in production. This approach aligns directly with the EU AI Act's focus on transparency, traceability, and ongoing risk management.

Harness helps in the following areas of the EU AI Act

AI System Inventory

Harness automatically discovers all AI assets—AI APIs, Agents, MCP servers, MCP tools, resources, prompts, and AI backends by analyzing live network traffic. The centralized inventory provides a real-time breakdown of discovered assets by type, call volume trends, and sensitive data exposure across your environment. Security and compliance teams gain a single, continuously updated source of truth for every AI component in use, without requiring manual cataloging or developer-submitted forms.

Risk Identification & Classification (Article 6)

Once assets are discovered, Harness derives a risk score for each based on policy violations, known vulnerabilities, exposure level (internal vs. external), and sensitive data flow. This scoring helps teams prioritize remediation efforts and demonstrate that high-risk AI systems have been identified and assessed, which is a core expectation under the EU AI Act's risk-based framework.

Prohibited Use Cases (Article 5)

Harness detects shadow AI vendors, unapproved MCP servers, and undocumented AI APIs surfacing in your environment. The Third Party view surfaces AI APIs grouped by vendor (e.g., OpenAI, Google, Anthropic) so teams can identify integrations that haven't undergone procurement or security review. This is directly relevant to the EU AI Act's prohibition on certain AI use cases and its requirements around supply chain transparency for AI systems.

Data Governance & Quality (Article 10)

Harness monitors sensitive data flows across all discovered AI assets, identifying where PII and regulated data enters and exits AI systems. The platform classifies data sensitivity automatically by analyzing asset metadata and observed traffic patterns, giving teams a continuous view of which assets handle sensitive information and surfacing misuse risks before they become compliance incidents.

Technical Documentation & Auditability (Articles 11, 16)

Harness automatically generates schemas for AI APIs, MCP tools, resources, and prompts by analyzing real network traffic with no manual documentation effort required. Each asset detail page captures the asset's type, dependencies, call volume, risk posture, and data flows in one place. This detail provides compliance teams with the structured technical records required under Articles 11 and 16 without burdening engineering teams with additional documentation.

Logging & Traceability (Article 12)

Harness captures all AI interactions, including AI API calls, MCP tool invocations, database calls, and non-AI API calls, in a centralized data lake with seven-day standard retention and 30-day retention for threat activity. This complete, queryable record of AI system behavior supports both routine audit needs and forensic investigations, directly satisfying Article 12's requirements for logging and traceability of high-risk AI systems.

Accuracy, Robustness & Security (Article 9)

The AI Firewall (beta) provides runtime enforcement against the most common AI-layer threats: prompt injection attacks, PII leakage in model responses, excessive model usage, and unauthorized model access. Together, these controls address the robustness and security requirements of Article 9, helping organizations demonstrate that their AI systems have active protections in place rather than passive policies.

Post-Market Monitoring (Article 72)

Harness continuously discovers new AI assets, shadow AI usage, and emerging sensitive data risks in production as your environment evolves. Real-time alerts are triggered for new vulnerabilities and compliance violations, with native integrations into SOC/SIEM workflows for rapid response. This ongoing monitoring capability aligns directly with the EU AI Act's post-market surveillance requirements, ensuring compliance doesn't end at deployment.

Bottom line: Harness AI Security provides the visibility, controls, and audit evidence layer required to operationalize EU AI Act compliance at scale and oversee AI system security. (Article 14)

Security teams face overwhelming amounts of data and complex interfaces, making it hard to access critical insights. AI tools promise solutions, but integration remains difficult as time ticks away and leadership wants the latest data to inform risk decisions.

Most security platforms lack seamless integration, slowing access to important data and hindering AI-powered workflows.

Introducing the Harness Web Application & API Protection (WAAP) MCP Server, a new solution that bridges the gap between security data and AI workflows. The capability empowers teams to serve security data to AI tools for faster, more intuitive insights. Make your security data accessible through natural-language prompts and directly consumable by MCP-compatible AI tools like Claude, VS Code, Cursor, and more.

With the Harness WAAP MCP Server, you’re no longer confined to dashboards for deep security insights, and you can power AI workflows, custom analysis, and executive-ready reporting.

Key Highlights

• AI-Native Security Access: Seamlessly connect Harness security data with LLM-powered assistants and copilots, enabling teams to access, analyze, and act on security insights without complex setup.
• Standardized Interface via MCP: The Model Context Protocol ensures consistent, reliable access to security data, reducing integration friction and eliminating proprietary barriers.
• Real-Time Threat Inspection: Instantly query live threat data, vulnerabilities, and API behavior, empowering teams to make faster decisions and reduce response times.
• Controlled Data Access: Easily manage access controls and governance, ensuring teams can integrate new solutions without adding security or compliance risk.

Why Security Teams Struggle Today

Harness builds its UI/UX to maximize functionality and customizability, adopting API-centric design and providing thorough API documentation. Being API-enabled is critical for system integrations and agentic workflows, but it’s an area where other solutions struggle. Despite significant investment or self-engineering, teams struggle to effectively leverage data from other security tools. 

Access is Unintuitive

Many traditional security platforms require users to navigate multiple dashboards, filters, and proprietary query builders. Even experienced users waste time finding the “right” data instead of acting on it. This friction is even more apparent when teams try to embed security into developer workflows or automation pipelines.

Lack of Integration Standards

Each platform uses its own data schemas, authentication models, and APIs, if any are even available. Integrating services or data into AI tools or other automated systems typically requires custom engineering, ongoing maintenance, and deep familiarity with the underlying system. It’s also a moving target, as vendors can change something and break integrations.

Security Data Isn’t AI-ready

Many security tools weren’t designed with LLMs or AI agents in mind. Data is frequently unstructured and inconsistently formatted. The data is also difficult to query, both conversationally and programmatically, which is fundamental for agentic workflows. This reality limits teams' ability to leverage AI to accelerate investigation, triage, and decision-making in security use cases such as vulnerability management and incident response.

Governance Is a Blocker

Even when teams want to publish security data safely, they must carefully manage permissions, ensure compliance, and prevent overexposure. This governance reality often leads to overly restrictive setups that negate the benefits of integration. The result is a disconnect: powerful security insights exist, but they’re too buried to find and act on.

Bring Security to AI Workflows with the Harness WAAP MCP Server

Security teams desire programmatic access to data via APIs for custom analysis and, increasingly, AI integration. The Harness WAAP MCP Server is designed to solve these challenges by providing a standardized, AI-friendly interface to your security data. The MCP server implements the Model Context Protocol, a de facto standard for enabling structured interactions between AI systems, data, and external tools. Instead of forcing you to engineer custom integrations, the MCP server empowers you to discover and interact with Harness security capabilities consistently and predictably.

Structured Access to Harness Data

The MCP server exposes key Harness security data, including threat detection, API inventory, vulnerability insights, and behavioral analytics. The data is served up with structured endpoints that AI tools can query directly. This design eliminates the need for manual navigation through dashboards or the need for custom API wrappers, saving time and enabling faster incident response. All of this happens through standardized MCP calls, making it easy to plug Harness security data into other AI ecosystems and workflows. 

Need a custom report for security leadership based on the context you define, not what the user interface dictates? The Harness WAAP MCP Server makes it possible with a simple prompt like:

“Generate me an executive summary of my overall security posture.
Format it in HTML/CSS/JS in a single report.html file.
Make the styling clean, modern, and professional.”

Simplified Integration

By using a standard protocol, the MCP server drastically cuts integration effort and complexity, enabling teams to use existing MCP-compatible clients for rapid, sustainable access to data in the Harness platform.

This standardization accelerates time-to-value, boosts tooling investments, and future-proofs integrations as the MCP ecosystem continues to grow. Combine nonsecurity and security data as you see fit. One of the most powerful aspects of MCP is composition.

Security teams are combining:

• Auto-discovered APIs from Harness API discovery
• Internally documented APIs
• Business metadata
• Environment and ownership data

They’re also doing this within custom AI workflows to answer questions that were previously painful or impossible with traditional tools.

Designed for Agentic AI

Traditional APIs often require rigid query construction, but the Harness WAAP MCP Server is optimized for dynamic, context-driven queries, ideal for use with LLM-based assistants and agentic workflows. Users or AI agents can ask questions like:

• “What is my overall security posture in production?”
• “Show me high-risk APIs handling PII with active threats.”
• “Which shadow APIs exist outside our internal documentation?”
• “What new threats were detected in the last 24 hours?”
• “Which AI-related APIs are transmitting PHI to 3rd party AI vendors?”
• “What API security anomalies occurred in the past 7 days?”

As an example, you can prompt for and interact with security data directly through Anthropic Claude via MCP:

The MCP layer translates these interactions into authenticated, structured queries against Harness’s backend security services, returning actionable insights in real time.

Secure by Design

Security is always paramount at Harness. The Harness WAAP MCP Server enforces strict authentication with a simple token-based approach. You control API key generation, rotation, and deletion. Enable your enterprise teams to confidently integrate security insights into AI workflows without compromising governance or compliance.

Get Started Today

Harness WAAP MCP Server is available immediately with your existing Harness subscription. There is no additional cost or setup required. Related technical documentation can be found here. 

Current Customers: Log in to your dashboard today to start exploring your security data in AI tools.

New to the Platform? If you aren't yet protected, contact us to schedule a personalized demo.

At SREday NYC 2026, the ShipTalk podcast welcomed Zachary Gruenberg, Solution Engineer and Machine Identity SME at Palo Alto Networks, for a conversation about one of the fastest growing challenges in modern infrastructure: machine identity management.

Throughout the conference, much of the discussion centered on AI agents automating operational tasks—from incident response to infrastructure management. But every automated agent interacting with systems still requires credentials and access permissions.

In the episode, ShipTalk host Dewan Ahmed, Principal Developer Advocate at Harness, spoke with Zachary about how the rapid rise of AI-driven automation is creating an explosion of machine identities—and why managing them is quickly becoming a major security concern for SRE and platform teams.

🎧 Listen to the Full Episode

The Explosion of Machine Identities

In the past, identity management primarily focused on human users logging into systems.

Today, the landscape looks very different.

Modern infrastructure environments include a growing number of non-human identities such as:

• service accounts
• automation scripts
• CI/CD pipelines
• microservices communicating with each other
• AI agents performing operational tasks

Each of these components requires credentials in order to interact with infrastructure, APIs, and other services.

As organizations deploy more automation and AI-driven workflows, the number of machine identities can quickly outnumber human users by several orders of magnitude.

For SRE teams, this creates a new challenge: tracking which systems have access to what resources—and ensuring those permissions remain secure.

Building Security That Scales with Automation

One of the most common problems Zachary sees is that teams prioritize functionality when deploying new automation systems.

When engineers introduce AI agents or automated workflows, identity management is often treated as an afterthought.

That approach can lead to:

• overly permissive service accounts
• long-lived credentials
• unclear ownership of machine identities
• difficulty auditing access across systems

To address this, Zachary encourages organizations to treat machine identity as a core component of their security architecture, rather than a secondary concern.

This often includes practices such as:

• implementing short-lived credentials
• centralizing identity management across services
• applying the principle of least privilege to machine accounts
• automating identity lifecycle management alongside infrastructure automation

When these controls are built into the platform early, security can scale alongside automation instead of becoming a bottleneck.

The Most Common Machine Identity Blind Spot

Despite the growing awareness of identity security, Zachary frequently encounters one recurring issue.

Many teams simply lose track of the machine identities they have created.

Over time, environments accumulate service accounts, API keys, tokens, and automation credentials that remain active long after the systems that created them are gone.

This “identity sprawl” can create significant risk, particularly in environments where automated systems are interacting with critical infrastructure.

The challenge becomes even greater as AI agents begin performing more complex operational tasks.

Ensuring that these agents have the right level of access—and no more—requires visibility into every identity operating within the system.

Security in an Autonomous Infrastructure World

As organizations adopt AI-driven automation across operations, the importance of identity security will only increase.

Each new automation tool or AI workflow adds another layer of machine identities interacting with infrastructure.

For SRE and platform teams, this means reliability engineering and security practices are becoming increasingly interconnected.

Strong machine identity management ensures that automation systems can operate safely while protecting the infrastructure they interact with.

‍

Final Thoughts

Zachary Gruenberg’s message is a timely reminder that the growth of AI agents and automation does not eliminate the need for strong security foundations.

If anything, it makes them even more critical.

As organizations move toward more autonomous systems, understanding who—or what—has access to critical infrastructure will remain one of the most important challenges for reliability and security teams alike.

🎧 Listen to the Full Episode

Subscribe to the ShipTalk Podcast

Enjoy conversations like this with engineers, platform builders, and reliability leaders from across the industry.

Follow ShipTalk on your favorite podcast platform and stay tuned for more stories from the people building the systems that power modern technology. 🎙️🚀

AI is changing both what you build and how you build it - at the same time. Today, Harness is announcing two new products to secure both: AI Security, a new product to discover, test, and protect AI running in your applications, and Secure AI Coding, a new capability of Harness SAST that secures the code your AI tools are writing. Together, they further extend Harness's DevSecOps platform into the age of AI, covering the full lifecycle from the first line of AI-generated code to the models running in production.

In November, Harness published our State of AI-Native Application Security report, a survey of hundreds of security and engineering leaders on how AI-native applications are changing your threat surface. The findings were stark: 61% of new applications are now AI-powered, yet most organizations lack the tools to discover what AI models and agents exist in their environments, test them for vulnerabilities unique to AI, or protect them at runtime. The attack surface has expanded dramatically — but the tools to defend it haven't kept up.

The picture is equally concerning on the development side. Our State of AI in Software Engineering report found that 63% of organizations are already using AI coding assistants - tools like Claude Code, Cursor, and Windsurf - to write code faster. But faster isn't safer. AI-generated code has the same vulnerabilities as human-written code, but now with larger and more frequent commits. AppSec programs that were already stretched thin are now breaking under the volume and velocity.

The result is a blind spot on both sides of the AI equation - what you're building, and what you're building with. Today, Harness is closing that gap.

What Makes Harness Different?

Most security vendors are stuck in their lane. Shift-left tools catch vulnerabilities in code before they reach production. Runtime protection tools block attacks after applications are deployed. And the two rarely talk to each other.

Harness was built on a different premise: real DevSecOps means connecting every stage of the software delivery lifecycle, and closing the loop between what you find in production and what you fix in code.

That's what the Harness platform does today. Application Security Testing brings SAST and SCA directly into the development workflow, surfacing vulnerabilities where they're faster and cheaper to fix. SCS ensures the integrity of artifacts from build to deploy, while STO provides a unified view of security posture — along with policy and governance — across the entire organization.

As code ships to production, Web Application & API Protection monitors and defends applications and APIs in real time, detecting and blocking attacks as they happen. And critically, findings from runtime don't disappear into a security team's backlog — they flow back to developers to address root causes before the next release.

The result is a closed loop: find it in code, protect it in production, fix it fast. All on a single, unified platform.

Today, we're extending that loop into AI - on both sides. AI is reshaping what you build and how you build it simultaneously. A platform that can only address one side of that equation leaves you exposed on the other. Harness closes both gaps.

Introducing AI Security

In the State of AI-Native Application Security, 66% of respondents said they are flying blind when it comes to securing AI-native apps. 72% call shadow AI a gaping chasm in their security posture. 63% believe AI-native applications are more vulnerable than traditional IT applications. They're right to be concerned.

Harness AI Security is built on the foundation of our API security platform. Every LLM call, every MCP server, every AI agent communicating with an external service does so via APIs. Your AI attack surface isn't separate from your API attack surface; it's an expansion of it. AI threats introduce new vectors like prompt injection, model manipulation, and data poisoning on top of the API vulnerabilities your teams already contend with. There is no AI security without API security. 

With the launch of AI Security, we are introducing AI Discovery in General Availability (GA). AI security starts where API security starts: discovery. You can't assess or mitigate risk from AI components you don't know exist. Harness already continuously monitors your environment for new API endpoints the moment they're deployed. Recognizing LLMs, MCP servers, AI agents, and third-party GenAI services like OpenAI and Anthropic is a natural extension of that. AI Discovery automatically inventories your entire AI attack surface in real time, including calls to external GenAI services that could expose sensitive data, and surfaces runtime risks, such as unauthenticated APIs calling LLMs, weak encryption, or regulated data flowing to external models.

Beyond discovering and inventorying your AI application components, we are also introducing AI Testing and AI Firewall in Beta, extending AI Security across the full discover-test-protect lifecycle.

AI Testing actively probes your LLMs, agents, and AI-powered APIs for vulnerabilities unique to AI-native applications, including prompt injection, jailbreaks, model manipulation, data leakage, and more. These aren't vulnerabilities that a traditional DAST tool is designed to find. AI Testing was purpose-built for AI threats, continuously validating that your models and the APIs that expose them behave safely under adversarial conditions. It integrates directly into your existing CI/CD pipelines, so AI-specific security testing becomes part of every release — not a one-time audit.

AI Firewall actively protects your AI applications from AI-specific threats, such as the OWASP Top 10 for LLM Applications. It inspects and filters LLM inputs and outputs in real time, blocking prompt injection attempts, preventing sensitive data exfiltration, and enforcing behavioral guardrails on your models and agents before an attack can succeed. Unlike traditional WAF rules that require manual tuning for every new threat pattern, AI Firewall understands AI-native attack vectors natively, adapting to the evolving tactics attackers use against generative AI. 

Harness AI Security with AI Discovery is now available in GA, while AI Testing and AI Firewall are available in Beta.

Introducing Secure AI Coding 

"As AI-assisted development becomes standard practice, the security implications of AI-generated code are becoming a material blind spot for enterprises. IDC research indicates developers accept nearly 40% of AI-generated code without revision, which can allow insecure patterns to propagate as organizations increase code output faster than they expand validation and governance, widening the gap between development velocity and application risk."

— Katie Norton, Research Manager, DevSecOps, IDC

AI Security addresses the risks inside your AI-native applications. Secure AI Coding addresses a different problem: the vulnerabilities your AI tools are introducing into your codebase.

Developers are generating more code than ever, and shipping it faster than ever. AI coding assistants now contribute to the majority of new code at many organizations — and nearly half (48%) of security and engineering leaders are concerned about the vulnerabilities that come with it. AI-generated code arrives in larger commits, at higher frequency, and often with less review than human-written code would receive.

SAST tools catch vulnerabilities at the PR stage — but by then, AI-generated code has already been written, reviewed, and often partially shipped. Harness SAST's new Secure AI Coding capability moves the security check earlier to the moment of generation, integrating directly with AI coding tools like Cursor, Windsurf, and Claude Code to scan code as it appears in the IDE. Developers never leave their workflow. They see a vulnerability warning inline, alongside a prompt to send the flagged code back to the agent for remediation — all without switching tools or even needing to trigger a manual scan.

"Security shouldn't be an afterthought when using AI dev tools. Our collaboration with Harness kicks off vulnerability detection directly in the developer workflow, so all generated code is screened from the start." — Jeff Wang, CEO, Windsurf

What sets Secure AI Coding apart from simpler linting tools is what happens beneath the surface. Rather than pattern-matching the AI-generated code in isolation, it leverages Harness's Code Property Graph (CPG) to trace how data flows through the entire application - before, through, and after the AI-generated code in question. That means Secure AI Coding can surface complex vulnerabilities like injection flaws and insecure data handling that only become visible in the context of the broader codebase. The result is security that understands your application - not just the last thing an AI assistant wrote.

We Had the Same Problem

When we deployed AI across our own platform, our AI ecosystem grew faster than our visibility into it. We needed a way to track every API call, identify sensitive data exposure, and monitor calls to external vendors — including OpenAI, Vertex AI, and Anthropic — without slowing down our engineering teams. 

Deploying AI Security turned that black box into a transparent, manageable environment. Some milestones from our last 90 days:

• We now track 111 AI assets and monitor over 4.76 million monthly API calls, giving our security team a granular, real-time map of our entire AI attack surface. 
• We now run 2,500 AI testing scans a week and have remediated 92% of the issues found, including critical weak authentication and encryption gaps in MCP tools.
• We identified and blocked 1,140 unique threat actors attempting more than 14,900 attacks against our AI infrastructure.

The shift wasn't just operational — it was cultural. We moved from reactive monitoring to proactive defense. As our team put it: "Securing AI is foundational for us. Because our own product runs on AI, it must be resilient and secure. We use our own AI Security tools to ensure that every innovation we ship is backed by the highest security standards."

Ready to Secure Your AI?

AI is moving fast. Your attack surface is expanding in two directions at once - inside the applications you're building, and inside the code your teams are generating to build them. 

Harness AI Security and Secure AI Coding are available now. Whether you're trying to get visibility into the AI running in your environment, test it for vulnerabilities before attackers do, or stop insecure AI-generated code from reaching production, Harness' platform is ready.

Talk to your account team about AI Security. Get a live walkthrough of AI Discovery, AI Testing, and AI Firewall, and see how your AI attack surface maps against your existing API security posture.

Already a Harness CI customer? Start a free trial of Harness SAST - including Secure AI Coding. Connect it to your AI coding assistant, and see what's shipping in your AI-generated code today.

Contact us