java-junit

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

• Third-party content exposure detected (high risk: 0.70). The skill's SKILL.md explicitly directs the agent to "consult Context7" and use the context7_resolve-library-id / context7_query-docs flow to fetch up-to-date docs (e.g., "/junit/junit5", AssertJ, Mockito) which are public third-party documentation pages the agent is expected to read and that could influence its actions.