caveman

Pass

Audited by Gen Agent Trust Hub on Oct 11, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill exclusively contains natural language instructions for text formatting and communication style.
  • [NO_CODE]: No executable scripts (Python, JavaScript, shell) are included or referenced.
  • [PROMPT_INJECTION]: The instructions for persistent behavior ('ACTIVE EVERY RESPONSE') are styling constraints for the agent's persona and do not attempt to bypass safety filters or exfiltrate data.
  • [INDIRECT_PROMPT_INJECTION]: While the skill modifies the agent's output style, it does not ingest untrusted external data or provide a vector for malicious instructions to influence the agent via processed content. It also includes an 'Auto-Clarity Exception' that prioritizes clarity for security-sensitive operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 11, 2026, 05:12 PM