audit-reply
Warn
Audited by Snyk on Jul 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Outsider-authored free text from GitLab MR discussions (reviewer/commenter bodies) is fetched at runtime via
glab api .../merge_requests/{iid}/discussionsinscripts/fetch_mr.py, then returned as JSON and ingested into the agent’s LLM context for Step 3/4 analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata