Agent Audit

Static security scanner for AI agent code covering prompt injection, MCP config auditing, and taint analysis.

Desktopfree

Agent Audit is an open-source static security scanner built specifically for AI agent code, detecting prompt injection, unsafe tool inputs, leaked secrets, and misconfigured MCP servers using tool-boundary-aware taint analysis. It maps its 72 detection rules to the OWASP Agentic Top 10 and supports frameworks like LangChain, CrewAI, and AutoGen, aimed at agent developers and security engineers who want CI-gated checks before deploying agent features.

Website

Full match profile

Behind the summary, Matchbox keeps a richer profile of Agent Audit - the signals our matcher actually reads to decide when to surface it. It stays private; claim the listing to see and control it.

Problem & pain-point mapping
Who we surface it to (audience fit)
What it's a strong alternative to
Trust & credibility signals

Claim Agent Audit to unlock →

Try Matchbox with your own problem

Describe what is not working - we’ll show you whether Agent Audit (or something else) actually fits.

Try a problem