HeadyZhang / agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 51 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
Why this job: says: security scanner; topics: security, ai-security, llm-security, prompt-injection, prompt injection
What it does
AI agents are not just chatbots. They execute code, call tools, and touch real systems, so one unsafe input path can become a production incident.
Get started
pip install agent-audit- Maintenance
- Active
- Last commit 57 days ago
- Stars
- 244
- On GitHub
- Licence
- MIT
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.20.0
- Released 57 days ago
- Built with
- Python
- 96% of the code
Is it looked after?
- Contributors
- 1
- Last 90 days
- Issues
- 57% closed
- 3 still open
- Pull requests
- 3 merged
- 3 waiting
- Releases
- 14
- 14 in the last year
- Contributing guide (opens in new tab)
- Security policy (opens in new tab)
- No code of conduct
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| OWASP / www-project-agent-memory-guard | 200 | today | Apache-2.0 | No downloads |
| asamassekou10 / ship-safe | 871 | 23 days ago | MIT | No downloads |
| sinewaveai / agent-security-scanner-mcp | 123 | 2 months ago | MIT | No downloads |
More: languages, topics and project record
Languages
- Python 96%
- Shell 3%
- TypeScript <1%
- JavaScript <1%
Topics
- ai-agent
- ai-security
- ai-security-tool
- cli
- crewai
- langchain
- langchain-security-
- llm-safety
- llm-security
- mcp
- owasp
- prompt-injection
Project record
- JobAI security
- StatusListed
- Commits168
- Forks30
- Watching3
- Stars in 28 days+7
- CreatedFeb 3, 2026
- First seen by usNov 7, 2026
- CheckedNov 7, 2026