do-execute-qa

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

• Third-party content exposure detected (high risk: 0.70). The skill's mandatory workflow (Step 3.1 and the MCP resolution in Step 0/Step 2 of SKILL.md) instructs the agent to use Context7 MCP to check framework documentation and explicitly falls back to Web Search if unavailable, which means the agent may fetch and interpret open/public web documentation (untrusted third-party content) as part of its testing decisions.