tgw-asset-cards

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the creation and updating of Markdown files within a specific local directory (tgw-data/). This behavior is the core purpose of the skill and is strictly controlled by logic requiring user confirmation and manual validation before any disk write operation is performed.
  • [SAFE]: The skill incorporates clear 'Human-in-the-loop' (HITL) requirements for sensitive business objects such as pricing, contracts, and refunds, preventing the AI from making autonomous decisions on critical matters.
  • [SAFE]: Analysis of the instructions and templates revealed no evidence of prompt injection, obfuscation, or unauthorized network activity. All external references are limited to local template paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 02:26 AM
Security Audit — agent-trust-hub — tgw-asset-cards