documentation-lookup

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow calls Context7 MCP tools (resolve-library-id and query-docs) to fetch documentation text from external documentation sources, which can include outsider-authored free text that is then ingested into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). This skill explicitly performs runtime calls to the external Context7 MCP (the resolve-library-id and query-docs tools) to fetch documentation and inject returned snippets into the agent's responses, so the remote MCP endpoint effectively controls the agent's prompts/outputs (Context7 MCP: resolve-library-id / query-docs).