ai-teaching-assistant-skills

Pass

Audited by Gen Agent Trust Hub on Jul 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a deterministic interface to an MCP (Model Context Protocol) server running on the host machine. The scripts (ta_client.py and setup_config.py) perform standard tasks such as API communication via the fastmcp library and local configuration management. No sensitive data exfiltration, malicious command execution, or obfuscation techniques were detected. The design explicitly discourages direct filesystem access by the user, requiring the use of generated browser URLs for uploads, which is a positive security pattern.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 22, 2026, 08:28 AM
Security Audit — agent-trust-hub — ai-teaching-assistant-skills