HeadyZhang/agent-audit
Static security scanner for LLM agents — prompt injection, MCP config auditing, taint analysis. 49 rules mapped to OWASP Agentic Top 10 (2026). Works with LangChain, CrewAI, AutoGen.
Platform-specific configuration:
{
"mcpServers": {
"agent-audit": {
"command": "npx",
"args": [
"-y",
"agent-audit"
]
}
}
}Add the config above to .claude/settings.json under the mcpServers key.
Loading reviews...