holistic-linting-resolver

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to fetch and read external documentation (e.g., using mcp__Ref__ref_read_url and a WebFetch fallback to public URLs like https://docs.basedpyright.com/) so the agent ingests open/public web content that can influence its fix/decision logic.