lyxy-runner-python

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly runs arbitrary Python scripts and "captures output" (SKILL.md Workflow step 5) and its docs list API interactions/HTTP requests as a typical scenario with concrete examples (references/examples.md showing requests.get to https://api.github.com/... and https://api.example.com), meaning it will execute code that fetches untrusted public web content which can influence decisions or next actions.