jwt

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 external website documentation via Context7 (using mcp__context7__resolve-library-id and mcp__context7__query-docs, preferring /websites/* IDs), meaning it will ingest untrusted public web content that could carry indirect prompt injection.