differential-review
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow reads and incorporates PR/commit/diff content (outsider-authored issue/PR text/code) into the LLM context via the “Phase 1: Changed Code Analysis” and subsequent phases that generate attack scenarios and reports from those diffs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata