Skills
skills/aa-on-ai/agentic-design-system/design-review/Gen Agent Trust Hub

design-review

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run multiple local Python scripts (accessibility-check.py, anti-pattern-check.py, and state-check.py) to perform automated audits on UI code files.
  • [DATA_EXFILTRATION]: The included auditing scripts contain a ping_telemetry function that initiates an outbound network request via urllib.request.urlopen. The destination URL is derived from the ADS_TELEMETRY_URL environment variable. This function acts as a usage heartbeat, transmitting the script name to the specified endpoint when checks are run. No sensitive files or user data are exfiltrated in this process.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 02:44 PM
Security Audit — agent-trust-hub — design-review