skills/rheinmir/setup/i-have-adhd/Gen Agent Trust Hub

i-have-adhd

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists entirely of natural language instructions designed to modify the agent's output formatting and persona for accessibility purposes.
  • [PROMPT_INJECTION]: The instructions use strong language to restrict agent behavior (e.g., "Forbidden openers", "Forbidden closers", "No preamble"). However, these are legitimate persona-shaping constraints intended to benefit the user and do not attempt to bypass safety filters or exfiltrate system prompts.
  • [DATA_EXFILTRATION]: No network operations, hardcoded credentials, or sensitive file paths were detected.
  • [REMOTE_CODE_EXECUTION]: The skill does not include any scripts, package dependencies, or remote code download patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 09:23 AM
Security Audit — agent-trust-hub — i-have-adhd