claude-code-mcp
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 config explicitly runs and connects to third-party MCP servers (e.g., via npx -y @modelcontextprotocol/server-postgres and remote HTTP transports configured in .claude/.mcp.json) so the agent will ingest and interpret outputs from public/untrusted packages and servers as part of its workflow.
Audit Metadata