w3osc/skill-warden

Scan AI skills for security threats - prompt injection, jailbreaks, secret grabbing, and more

View on GitHub

Trust Signals

Scorecard Score
not yet scored
Maintenance Recency
Stale
License
None
namedescriptionrequireddefault
targetGitHub URL or local path to skill(s) to scan. Defaults to the repository root.no${{ github.workspace }}
output-formatOutput format: pretty, json, sarifsarif
sarif-filePath to write SARIF output fileskill-warden-results.sarif
fail-on-advisoryFail the action if advisory violations are foundfalse
github-tokenGitHub token for private repositories${{ github.token }}
upload-sarifUpload SARIF results to GitHub Security tabtrue
no-qualitySkip quality checksfalse
no-ai-scoreSkip AI slop scoringfalse
namedescription
hard-passedWhether all hard security checks passed (true/false)
has-advisoriesWhether advisory violations were found (true/false)
sarif-filePath to the SARIF output file