native-mcp
Warn
Audited by Snyk on Sep 5, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill connects to Model Context Protocol (MCP) servers, which can be community-authored or remote servers that ingest external input, creating an indirect prompt injection risk when their tools or sampling requests are processed by the agent.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata