python-executor

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly shows and instructs running Python that fetches and parses arbitrary public web content/APIs (e.g., the "Web Scraping" example requests https://example.com and the "API Calls" example hits https://api.github.com), so untrusted third-party content can be ingested and influence execution.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Start instructs running "curl -fsSL https://cli.inference.sh | sh" (which downloads and executes remote installer code from https://cli.inference.sh and subsequent binaries from dist.inference.sh), so the skill relies on fetching and executing remote code as a required dependency.