skill-writer
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [Prompt Injection] (SAFE): No attempts to override system prompts or bypass safety filters were detected. The instructions are focused on guiding the user through a specific task.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations were found. References to local directories like ~/.claude/skills/ are standard for the intended application context.
- [Unverifiable Dependencies & Remote Code Execution] (SAFE): While the skill mentions command-line tools like pip and python, these are within code block templates meant for the user to implement. The skill itself does not perform any remote code downloads or unauthorized executions.
- [Command Execution] (SAFE): Shell commands listed (mkdir, ls, cat) are provided strictly for documentation purposes and as templates for the user to create the necessary directory structure for their own skills.
Audit Metadata