boss
Warn
Audited by Snyk on May 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: 0.90). The skill's Architect and PM agents explicitly perform web research using WebSearch/WebFetch ("agents/boss-architect.md" 技术调研阶段: "使用 WebSearch 搜索技术方案" / "使用 WebFetch 获取文档详情"; "agents/boss-pm.md" 调研验证阶段 similarly), meaning the agents fetch and interpret open/public third‑party content (untrusted web pages/competitor analyses) as required inputs that can materially influence architecture/implementation decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata