caveman

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely instructional and focused on persona modification. It defines a 'Caveman Mode' to help reduce token consumption by stripping filler words and articles while maintaining technical accuracy.
  • [EXTERNAL_DOWNLOADS]: The file contains a reference to a GitHub repository (github.com/mattpocock/skills) for attribution purposes. This is a well-known source and is used here in a purely informational capacity.
  • [PROMPT_INJECTION]: There are no attempts to bypass safety filters or override system instructions in a malicious way. The instructions are transparent and include explicit exceptions for security warnings and HIPAA-sensitive data to ensure clarity and safety.
  • [DATA_EXFILTRATION]: No network operations, sensitive file access, or credential harvesting patterns were detected.
  • [COMMAND_EXECUTION]: The skill does not contain any scripts, shell commands, or dynamic code execution patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 02:51 PM