oh-ci
Warn
Audited by Snyk on Aug 6, 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). In SKILL.md the runtime path uses GitHub CLI APIs to fetch CI check-run annotations and logs for a PR’s failing checks (including arbitrary log/annotation text) via
gh api .../check-runs/.../annotationsandgh run view "$RUN_ID" --log-failed, which can include outsider-authored content from the PR or CI outputs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata