skills/vm0-ai/vm0-skills/exa/Gen Agent Trust Hub

exa

Pass

Audited by Gen Agent Trust Hub on Jun 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Uses standard command-line tools (curl, jq) to interact with the Exa API. These operations are scoped to the intended functionality of web search and content retrieval.
  • [EXTERNAL_DOWNLOADS]: Interacts with api.exa.ai, which is a well-known service for AI-native search. No executable code is downloaded or executed from the network.
  • [CREDENTIALS_UNSAFE]: Appropriately manages authentication by referencing the EXA_TOKEN environment variable rather than hardcoding sensitive credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 14, 2026, 01:52 AM
Security Audit — agent-trust-hub — exa