NYC

recovery-education-writer

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE] (SAFE): Analysis of the README, example output, and reference materials reveals no malicious intent, obfuscation, or safety bypasses.
  • [NO_CODE] (SAFE): The skill consists entirely of markdown files and does not include any Python, JavaScript, or shell scripts that could be executed by the agent.
  • [DATA_EXFILTRATION] (SAFE): No network requests (curl, wget, fetch) or sensitive file path access (SSH keys, AWS credentials) were identified.
  • [PROMPT_INJECTION] (SAFE): The instructions focus on content structure and voice guidelines without attempting to override system prompts or disable safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:27 PM