hiascend-forum-fetcher

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

• Third-party content exposure detected (high risk: 0.80). This skill explicitly fetches user-generated posts from the public Hiascend forum API (https://www.hiascend.com/ascendgateway/.../get-topic-list) as documented in SKILL.md and implemented in fetch_page/fetch_all_topics, and it parses post fields (e.g., createTime, top) to make runtime decisions (filtering and intelligent termination), so untrusted third‑party content can materially influence agent behavior.