mantis-review
Warn
Audited by Snyk on Sep 14, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill reads finding JSON files from
workspace/findings/, which contain outsider-submitted analysis and claims, representing an indirect prompt injection risk from untrusted content in the monitored workspace directory.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata