create-tooluniverse-skill

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (e.g., SKILL.md, QUICK_START.md, python_implementation.py, and the test scripts) explicitly instructs calling ToolUniverse tools (tu.tools.*) to query public third-party databases (examples: Reactome, HMDB, IMGT/SAbDab and other external databases) and to read/interpret those responses to drive analysis, fallback logic, and next actions, so untrusted external content could materially influence behavior.