dubwerk/skill-scan

Security scanner for agent skills — detect prompt injection, malicious code, and data exfiltration

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
pathPath to the skill directory to scan (local)no.
repoGitHub repository to scan (owner/repo or owner/repo@ref)no""
fail-onExit with code 2 if any finding at or above this severity (critical, high, medium, low, info)no""
formatOutput format: text, json, or sarifnotext
configPath to skill-scan config fileno""

no outputs