claude-api-ops

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes a helper script designed to verify the accuracy of model metadata by fetching data from official sources.\n
  • Evidence: The script scripts/check-model-table.py connects to https://api.anthropic.com/v1/models to retrieve live model information.\n
  • Context: These network requests target a well-known, official service endpoint and are used for documentation maintenance.\n- [COMMAND_EXECUTION]: A utility script within the skill executes a system command to perform network requests.\n
  • Evidence: scripts/check-model-table.py uses subprocess.run to invoke the curl binary.\n
  • Context: The command is executed with hardcoded parameters and targets official API endpoints, presenting no risk of arbitrary command injection or unauthorized access.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:50 PM
Security Audit — agent-trust-hub — claude-api-ops