implement-eval
Warn
Audited by Snyk on Aug 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required runtime workflow only conditionally reads GitHub issue content when the user supplies a GitHub issue number/URL (via GitHub integration or
gh), which is outsider-authored free text that the LLM can ingest without pre-selecting a specific trusted item beyond the user-provided reference.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata