multi-agent-architecture
Warn
Audited by Snyk on Mar 13, 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.md config explicitly defines a "news" agent whose system prompt instructs it to "抓取真实新闻" and the agent's config allows the "web_fetch" tool (News Agent config in SKILL.md), meaning it will fetch and read open public web content that could contain untrusted third-party instructions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata