axiom
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is implemented as a set of markdown files providing a logic-based framework. It does not include any scripts, dependencies, or commands.
- [SAFE]: No network access or data exfiltration mechanisms were detected. The skill does not access sensitive local files or hardcoded credentials.
- [PROMPT_INJECTION]: The Anti-Sycophancy Rules in SKILL.md use strong override language to shape the agent persona. While this matches behavioral override patterns, it is intended to promote analytical objectivity rather than bypass safety filters or extract system information.
Audit Metadata