library-docs-skill-creator

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly instructs the agent to use the Task tool (Explore subagent) to research and ingest content from public GitHub repositories and external documentation sites (e.g., exploring repos like pydantic/pydantic and separate docs/example repos), which are untrusted, user-generated third-party sources the agent will read and interpret.