ai-accessibility

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses a Python runner script (scripts/run.py) to communicate with the vendor's API endpoint at https://ai-skills.ai/api/execute. This is the documented and intended method for skill execution.
  • [DATA_EXFILTRATION]: User-supplied parameters (such as goal, materialUrl, and materialText) are transmitted to the vendor's service for analysis. No patterns suggesting unauthorized access to or exfiltration of sensitive local system files (e.g., SSH keys, AWS credentials) were detected.
  • [CREDENTIALS_UNSAFE]: The skill instructs users to manage their API keys via environment variables (AISKILLS_API_KEY), which is a recommended best practice for secure credential management.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:30 AM
Security Audit — agent-trust-hub — ai-accessibility