fix
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's "pr-comments" workflow explicitly uses "github-search (fetch PR context)" to read PR comments and context—user-generated, potentially public GitHub content—which the agent ingests and acts on, exposing it to untrusted third-party input.
Audit Metadata