action-audit
Warn
Audited by Snyk on Apr 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly instructs the agent to fetch and parse workflow files and action repos via
gh search codeandgh api repos/<owner>/<repo>/commits/<ref>, which ingests user-generated content from public GitHub repositories (third-party actions and workflow files) and uses those results to decide remediation and resolved SHAs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata