rexcoleman/Agent Skill Scanner

Scan agent skill files for security vulnerabilities. 22 rules across prompt injection, capability escalation, data exfiltration, encoded payloads, and composition risks.

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
pathPath to scan (file or directory)no.
min-severityMinimum severity to report (CRITICAL, HIGH, MEDIUM, LOW, INFO)noINFO
fail-on-findingsFail the step if HIGH or CRITICAL findings are detectednotrue
scanner-versionVersion of agent-skill-scanner to install from PyPIno0.1.0
namedescription
findings-countTotal number of findings detected
exit-codeScanner exit code (0=clean, 1=findings)