to-goal
Warn
Audited by Snyk on Aug 22, 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, the runtime workflow requires reading outsider-supplied tracker/spec/ticket text via inputs like “a ticket number or URL” (“read that ticket in full”) or “an unblocked … frontier ticket,” meaning the agent ingests user/externally authored free text from those ticket sources at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata