daily-trending

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly instructs the agent to fetch and parse public pages on tophub.today (see the "数据获取" section and web_fetch examples like web_fetch("https://tophub.today/n/KqndgxeLl9")), so the agent ingests untrusted, user-generated/open-web trending content and must interpret it to decide which items to output, which could allow indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill makes runtime web_fetch calls to tophub.today (e.g., https://tophub.today/n/KqndgxeLl9 and other https://tophub.today/n/... pages) and relies on the fetched page content to drive the agent's output/context, meaning external content directly controls the agent's responses.