review
Warn
Audited by Snyk on Jul 7, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The required workflow feeds the integrated diff (which includes outsider-authored PR/branch text) into the subagent’s LLM context via the orchestrator’s “review_diff” step that passes “the diff content” to the spawned reviewer.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata