context7-docs

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly calls Context7 MCP (e.g., mcporter call context7.query-docs against https://mcp.context7.com/mcp) to fetch up-to-date documentation and code snippets from external sources and its Integration Pattern instructs subagents to "Use returned docs/snippets in implementation," meaning untrusted third-party content is ingested and can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill configures and calls the Context7 MCP endpoint (https://mcp.context7.com/mcp) at runtime via mcporter to fetch documentation and code snippets that are then injected into subagent implementations, meaning remote content can directly control prompts/behavior.