task-prd-creator

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow (references/full-guide.md Step 4 "Fetch Latest Library Docs (MANDATORY)") instructs the agent to fetch external library documentation via Context7 MCP (e.g., mcp_context7_get_library_docs("/vercel/next.js", ...)), which ingests public third‑party website content that the agent must read and that can materially influence implementation decisions.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill mandates runtime fetching of external library docs via Context7 MCP (e.g., mcp_context7_get_library_docs("/vercel/next.js", ...) and mcp_context7_get_library_docs("/nestjs/docs.nestjs.com", ...)), which would inject externally-fetched content into the agent's context and thereby directly influence prompts/instructions.