slides
Warn
Audited by Snyk on Mar 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow explicitly instructs using "WebSearch 搜索相关信息" in "第二步:构思讲稿" to fetch web content (and also relies on external resources like Google Fonts CDN), so the agent will ingest untrusted public web content that can influence script/slide generation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata