unit-testing

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly requires using context7 (e.g., "context7 resolve " and "context7 get-library-docs") to fetch testing framework documentation from external/public sources, so the agent will ingest and interpret untrusted third-party content as part of its workflow.