create-pr
Warn
Audited by Snyk on Jul 10, 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 required workflow polls and reads PR comments/reviews/inline thread bodies via
gh api/GraphQL (outsider-authored PR discussion content) and then uses that text to classify/respond, so the LLM can ingest free-form third-party text at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata