apm-spec-guardian
Warn
Audited by Snyk on Jun 29, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s Wave 3 panel fan-out passes the PR body and full diff inline into each panelist task prompt; those fields are outsider-authored free text (PR author/other contributors) and the panelist outputs are then incorporated into the synthesizer and rendered comment context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata