skills/johnefemer/skillfish/caveman/Gen Agent Trust Hub

caveman

Pass

Audited by Gen Agent Trust Hub on Jul 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTIONNO_CODE
Full Analysis
  • [SAFE]: No malicious behavior, obfuscation, or sensitive data access patterns were detected. The skill functions as a legitimate productivity utility for token optimization.
  • [NO_CODE]: The skill file (SKILL.md) consists entirely of metadata and instructional documentation. It does not contain any executable scripts, binaries, or active code components.
  • [EXTERNAL_DOWNLOADS]: The skill documentation provides instructions to fetch and install the skill from an external GitHub repository (github.com/JuliusBrussee/caveman) using platform-specific plugin managers such as npx, claude plugin, and gemini extensions.
  • [PROMPT_INJECTION]: The skill's primary functionality is based on modifying the agent's system persona to use a specific linguistic style. While this is a form of behavioral instruction, it is the intended functional purpose and does not attempt to bypass security guardrails.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 4, 2026, 12:46 AM
Security Audit — agent-trust-hub — caveman