plan-design-review
Warn
Audited by Snyk on Nov 16, 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 reads git history and runs a Codex outside-voice pass with
web_search="cached", so outsider-authored text can reach the agent through commit messages or web results it fetches, but the agent does not monitor an open feed.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata