summarize

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly fetches and summarizes/transcribes arbitrary public URLs and YouTube links (e.g., "summarize "https://example.com\"" and YouTube examples), so the agent ingests untrusted third‑party web/video content and uses it to drive follow‑up actions and outputs.

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

• Potentially malicious external URL detected (high risk: 0.80). This skill fetches arbitrary external URLs at runtime (e.g., https://example.com and https://youtu.be/dQw4w9WgXcQ) and injects that fetched content into the model prompt to produce summaries, so remote content can directly control agent instructions.