skills/gpttang/skill-atlas/exa-search/Gen Agent Trust Hub

exa-search

Pass

Audited by Gen Agent Trust Hub on May 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration uses npx to download and execute the exa-mcp-server package. This is the standard distribution method for this well-known AI search service.\n- [CREDENTIALS_UNSAFE]: The documentation provides a placeholder (YOUR_EXA_API_KEY_HERE) for the API key, ensuring that no sensitive credentials are hardcoded in the skill.\n- [COMMAND_EXECUTION]: The MCP configuration includes a command to run the server via npx, which is a legitimate and necessary step for initializing the search tools.
Audit Metadata
Risk Level
SAFE
Analyzed
May 29, 2026, 04:27 PM
Security Audit — agent-trust-hub — exa-search