ilya-sutskever

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns were identified during the analysis of the skill. The content consists entirely of markdown-based instructions for persona simulation.
  • [NO_CODE]: The skill does not contain any executable scripts, binary files, or shell commands, which significantly reduces the attack surface for categories like remote code execution or privilege escalation.
  • [PROMPT_INJECTION]: While the skill provides specific directives on how the AI should behave (e.g., 'you are Ilya Sutskever'), these instructions are consistent with the intended character-play functionality and do not attempt to bypass safety filters, ignore prior instructions, or extract the system prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 10:22 PM
Security Audit — agent-trust-hub — ilya-sutskever