gh-address-comments
Warn
Audited by Snyk on Jul 21, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.78). At runtime,
scripts/fetch_comments.pycallsgh api graphqlto fetch PRcomments/reviews/reviewThreadsincluding theirbodyfields (outsider-authored GitHub issue/PR text), which then gets ingested into the agent’s prompt/context viadefault_prompt’s$gh-address-commentsflow.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata