setup-expert-feedback-remote-tool

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and installs a Python wheel from 'https://connect.aiscientist.tools/'. This is treated as a vendor-specific resource for 'mims-harvard' and follows security best practices by including a SHA-256 hash ('3fad5eee5ecf7887a693d93ccd1aa112dc0955617a885d1fc3daded0030f9ae0') to ensure integrity.
  • [COMMAND_EXECUTION]: The skill provides instructions for creating virtual environments, installing packages via pip, and running a local Flask/MCP server for tool testing. These are standard development operations.
  • [DATA_EXPOSURE]: The documentation explicitly warns against putting credentials in shell arguments or Git, and suggests using protected environment variables or 0600-permissioned files for keys, reflecting good security posture.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 08:19 AM
Security Audit — agent-trust-hub — setup-expert-feedback-remote-tool