skills/ernesto27/skills/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a set of behavioral instructions for the AI agent to modify its response style to be more concise. These instructions do not attempt to bypass core safety guardrails or system prompts.
  • [SAFE]: No executable code, shell scripts, or external dependencies are present in the skill definition. The skill operates entirely through natural language instructions.
  • [SAFE]: The skill includes a "Auto-Clarity" section that explicitly instructs the agent to prioritize clear, standard communication over the "caveman" persona when delivering security warnings or confirming irreversible actions, which is a defensive best practice.
  • [SAFE]: No evidence of data exfiltration, sensitive file access, or network communication was found. The skill is entirely self-contained within the provided instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 05:17 PM
Security Audit — agent-trust-hub — caveman