build-cognitive-source-driven

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md’s “Source-Driven 流程” requires a DETECT → FETCH step that performs web search and reads official documentation/GitHub/type definitions to verify API signatures, so it can ingest outsider-authored free text from search results/pages when those are read at runtime (even though it prefers P0-P3).