ship

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly instructs the agent to load /research and perform "web search when needed" to verify third‑party libraries/APIs and to use /browser and /screengrabs in Phase 1–3, which requires fetching and interpreting content from public third‑party websites and documentation that can materially influence implementation decisions and tool use.