code-implementation

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

• Third-party content exposure detected (high risk: 0.80). The SKILL.md Step 1 "Look up external docs" explicitly instructs the agent to use context7 resolve-library-id + query-docs or WebSearch to fetch public external documentation/web pages, which are untrusted third‑party content the agent will read and use to guide coding decisions and tool use.