creation-guard
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is restricted to local file system operations using Read, Glob, and Grep tools. These operations are limited to project-specific directories (skills/ and .claude/agents/) and do not access sensitive system files or credentials.
- [SAFE]: There are no network capabilities or external dependencies configured in the allowed-tools or instructions, preventing unauthorized data transmission or remote code execution.
- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found in the instructions or metadata.
- [SAFE]: The skill operates in an advisory capacity, requiring user confirmation (AskUserQuestion) before any significant actions are taken, maintaining human-in-the-loop control.
Audit Metadata