china-client-review
Warn
Audited by Snyk on Jun 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: 0.72). The skill’s runtime workflow ingests market/portfolio text via external MCP tools (e.g., iFind MCP / AkShare MCP) and other third-party data providers (Wind/Choice), which are outsider-authored sources whose returned readable content can be fed into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata