cw-asshole

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The skill consists entirely of markdown-based instructions for an AI persona. It does not include any scripts, dependencies, or command-line executions.
  • [SAFE]: The skill defines a specific behavioral persona ("Asshole Reader") for the purpose of identifying logical flaws and weaknesses in writing. It does not attempt to bypass safety filters for malicious purposes, nor does it access or exfiltrate sensitive data. All processing occurs within the standard text-based interaction between the user and the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 06:42 PM
Security Audit — agent-trust-hub — cw-asshole