x-collect
Warn
Audited by Snyk on May 20, 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). SKILL.md explicitly requires the WebSearch tool and directs the agent to perform four rounds of web searches (e.g., "Search: '{topic} 官方文档'", GitHub queries, and public URLs such as https://modelcontextprotocol.io/docs) and then synthesize those public, user-generated/untrusted web results into reports, so the agent will ingest third-party web content that can materially influence its outputs and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata