headyzhang/Agent Audit

Security scanner for AI agents and MCP configurations. Detects vulnerabilities based on OWASP Agentic Top 10.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Activelast commit Jul 3, 2026
License
MIT

Pinned Snippet

workflow.ymlSHA-pinned
uses: headyzhang/agent-audit@c3e6ce6249b3755dbef01108dcda7d00325b1d84 # v0.19.0

tags can be moved; commit SHAs can't. why a SHA?

namedescriptionrequireddefault
pathPath to scan (default: current directory)no.
formatOutput format: terminal, json, sarif, markdownnosarif
outputOutput file path (required for sarif format)noagent-audit-results.sarif
severityMinimum severity to report: info, low, medium, high, criticalnolow
fail-onExit with error if findings at this severity: low, medium, high, criticalnohigh
baselinePath to baseline file for incremental scanningno
upload-sarifUpload SARIF to GitHub Security tab (true/false)notrue
namedescription
total_findingsTotal number of security findings detected
critical_countNumber of CRITICAL severity findings (security-severity >= 9.0)
high_countNumber of HIGH severity findings (security-severity >= 7.0, < 9.0)
medium_countNumber of MEDIUM severity findings (security-severity >= 4.0, < 7.0)
low_countNumber of LOW severity findings (security-severity < 4.0)
scan_statusScan status: success (exit code 0) or failure (findings exceed fail-on threshold)
sarif_filePath to the generated SARIF file (if format=sarif)
findings-countTotal number of findings (deprecated: use total_findings)
exit-codeExit code from scan (deprecated: use scan_status)