context7

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

• Third-party content exposure detected (medium risk: 0.30). In the context7 skill, the runtime path _get_context(library_id, query, tokens) calls the Context7 /api/v2/context endpoint and returns resp.read().decode(), which is LLM-readable documentation text that is retrieved based on attacker-supplied free-form library_id/query inputs.