web-content-fetcher

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

• Third-party content exposure detected (high risk: 1.00). This SKILL.md explicitly instructs the agent to fetch and ingest arbitrary public web pages and social-media/user-generated content (e.g., X/Twitter, 微信, 知乎, Medium) via WebFetch and proxy prefixes like https://r.jina.ai/ and https://defuddle.md/, so untrusted third-party content will be read and can influence agent behavior.