Cloudflare open-sources an AI security audit skill
Cloudflare has lifted the lid on its internal vulnerability-discovery harness and open-sourced security-audit-skill: a set of skills that turns a coding agent (Claude Code, Copilot and friends) into a structured security auditor.
Six phases, a complete audit workflow
The workflow comes in six phases: reconnaissance of the architecture and attack surfaces, vulnerability hunting driven by a coverage registry, validation of each candidate, structured JSON output, independent verification of results, final report.
Separation of duties is the real intelligence
Cloudflare made a smart call: the agent that finds a finding never validates it itself. A second, clean agent receives the discovery with a single mission — refute it. Findings that survive go to "confirmed", those missing exact proof stay in "needs_validation" with no severity assigned, the rest are "rejected".
The attack classes covered go far: supply chain and CI/CD, IAM and InfraAsCode, containers, serverless, prompt injection on targets embedding an LLM, resource exhaustion.
The problem it solves: audit hallucination
AI-driven security audits suffer a known problem: the model hallucinates vulnerabilities or misses half of them, and nobody knows which. Here, coverage is tracked in a ledger, runs are additive (the skill reuses previous audits to target the gaps) and every final claim passes through an independent agent. On projects already reviewed manually, the Cloudflare set surfaced findings that had been missed.
A standard CI step in the making?
Tools like this are likely to become a standard step in CI pipelines within two years, just like SAST and DAST: a skill-based audit between lint and tests, on every merge.
Still, a tool doesn't do everything. Cloudflare says it themselves on their blog: the skill grew to run at the scale of their fleet, but their real asset is process discipline rather than the model under the hood.
Hacking & AI. An audit harness open to everyone — the question is no longer whether your agents will audit your code, but when.