python3-development

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

• Third-party content exposure detected (high risk: 0.90). The skill's bundled documentation explicitly instructs the agent to WebFetch external URLs (e.g., references/PEP723.md: "The model must WebFetch this url before discussing the topic with the user pep-0723") so the agent is required to fetch and interpret public third‑party webpages which could contain untrusted, user-controlled content that may influence its tool use and decisions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's PEP 723 reference explicitly instructs the model to "must WebFetch" external resources at runtime (e.g. https://peps.python.org/pep-0723/ and https://packaging.python.org/en/latest/specifications/inline-script-metadata/#inline-script-metadata), so the agent would fetch remote content that directly controls its prompt/context before responding.