to-tickets
Warn
Audited by Snyk on Jul 23, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). SKILL.md:11-11 requires reading “reference … spec path、issue number 或 URL” from the provided parameters and “获取并完整读取其 body 和 comments,” which (if the reference is outsider-authored) becomes readable text in the agent’s context via the runtime reference-fetch/body+comments ingestion path.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata