ai-engineering-review
Warn
Audited by Snyk on Nov 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow's only outsider-reachable input is Phase 6's live WebSearch/WebFetch of provider facts, where search results and fetched pages are outsider-authored text the agent must actively retrieve (restricted to official domains, but not guaranteed); the reviewed code, plans and prompts are the user's own files, and PR text is only an optional framing source.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata