Skills
skills/alphaonedev/openclaw-graph/exa-web-search/Gen Agent Trust Hub

exa-web-search

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Python subprocess module to interact with the exa command-line utility for search operations.
  • [PROMPT_INJECTION]: The skill extracts content and highlights from external websites, creating a vulnerability surface for indirect prompt injection if retrieved data contains adversarial instructions.
  • [SAFE]: The skill communicates with the official Exa.ai API and manages authentication via environment variables, following standard security patterns for search tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 10:46 PM