history-autopsy
Warn
Audited by Snyk on Feb 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). Flagged because the skill's Hotspot Judgment Flow explicitly requires calling the search_web tool to query "本周国际新闻热点" / "今日重大新闻" and extracting 2–3 topics from those public web search results, which are untrusted third‑party content the agent must read and interpret.
Audit Metadata