li-xiaolai-perspective
Warn
Audited by Snyk on Apr 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). Flagged because SKILL.md Step 2 explicitly requires the agent to "必须使用真实信息源" (must use real information sources) and the repo includes a references/sources directory (e.g., references/sources/articles/sources.md) listing public URLs like http://lixiaolai.com and other external pages, which the agent is expected to fetch and interpret as part of its research workflow and that research materially influences its conclusions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata