mcp-server-id-mapping
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill references spawning a Node.js process (
node legiox-mcp-server.js --test) as a health check within a packager CI environment. This is presented as a development pattern for verification. - [INDIRECT_PROMPT_INJECTION]: The instructions involve reading external tool descriptor JSON files from paths like
mcps/*/tools/*.jsonto ensure schema compatibility before tool invocation. This identifies a surface where untrusted data could be ingested into the agent context. - Ingestion points: External tool schemas and metadata files located in
mcps/*/tools/*.jsonand~/.cursor/projects/*/mcps/. - Boundary markers: Not specified in the instructions.
- Capability inventory: Mentions the use of
CallMcpToolandnodesubprocess execution for testing. - Sanitization: The skill focuses on ID mapping and schema validation rather than input sanitization.
Audit Metadata