github-workflow
Warn
Audited by Snyk on May 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). This skill's SKILL.md (Workflow step 3) explicitly requires fetching inline comments and review bodies from GitHub pull requests—user-generated, potentially public third-party content—which the agent is expected to read and act on, allowing indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata