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.py calls gh api graphql to fetch PR comments/reviews/reviewThreads including their body fields (outsider-authored GitHub issue/PR text), which then gets ingested into the agent’s prompt/context via default_prompt’s $gh-address-comments flow.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 12:23 AM
Issues
1
Security Audit — snyk — gh-address-comments