NYC

axiom-using-axiom

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • PROMPT_INJECTION (LOW): The skill uses high-pressure, absolute language designed to override the agent's autonomy and default instruction-following behavior. Phrases like 'ABSOLUTELY MUST', 'NOT NEGOTIABLE', and 'YOU DO NOT HAVE A CHOICE' are typical prompt injection markers that force specific tool usage regardless of user context.
  • NO_CODE (SAFE): No scripts or executable files are included in this skill, which limits the potential for direct technical exploitation or data exfiltration.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 01:41 AM