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 shows the skill fetching and summarizing arbitrary public URLs and YouTube links (e.g., "summarize "https://example.com\"" and YouTube examples), so the agent reads untrusted third‑party content and uses it to drive its outputs, enabling indirect prompt injection.