news
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflow explicitly instructs the agent to use webpage search/reader tools and "全网检索" (and fallback curl/wget) to fetch and read public web pages and arbitrary URLs as part of news verification, so it ingests untrusted third-party web content.
Audit Metadata