verification-before-completion
Warn
Audited by Snyk on Nov 12, 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 the local repository, command output, and the user's own instruction files, but its review-staleness and merge/approve guidance (change-strategies.md) requires fetching and re-checking a selected PR's state and prior human reviews, which are outsider-authored text the agent must actively retrieve.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata