pre-release-review
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.65). The required workflow can ingest outsider-authored free text when it fetches and reads a PR diff via
gh pr view/gh pr diff(PR body/diff content authored by non-operating users) and then uses that diff as evidence in the LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata