sitrep
Warn
Audited by Snyk on Aug 8, 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). In SKILL.md Step 2/3/4, the required runtime reads lane outputs produced from gatherer-protocol.md, which in its BACKBONE lane explicitly reads in-repo handoff/pause markdown and scans them for markers, and that file text is outsider-authored if an outsider can write those files (e.g., via monitored queue/feed/file submission), making it an indirect prompt-injection surface.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata