tooling-engineer

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely composed of natural language instructions and JSON data templates. It does not include any executable scripts or binary files.
  • [SAFE]: No prompt injection, obfuscation, or data exfiltration patterns were identified. The instructions focus on tool design and developer productivity.
  • [SAFE]: The skill restricts tool usage by setting allowed-tools to an empty string, preventing the agent from performing unauthorized actions.
  • [SAFE]: References to external JSON files are local and used for structured communication or tracking rather than remote code execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 04:15 AM
Security Audit — agent-trust-hub — tooling-engineer