weaponized-autism
Pass
Audited by Gen Agent Trust Hub on Jun 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists purely of natural language instructions designed to improve auditing quality and analytical depth. It encourages thorough file reading, assumption verification, and edge-case analysis.
- [PROMPT_INJECTION]: No evidence of prompt injection, role-play jailbreaks, or safety bypass attempts was found. The instructions focus on rigorous evidence-based reasoning rather than overriding system constraints.
- [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file path references (e.g., .ssh, .aws) are present in the skill.
- [COMMAND_EXECUTION]: No shell commands, scripts, or privilege escalation patterns (like sudo) were detected. The skill uses standard markdown and YAML frontmatter.
Audit Metadata