caveman-help

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a static help guide for users. It does not perform any file system modifications, network requests, or command executions.
  • [EXTERNAL_DOWNLOADS]: The skill includes a reference to a project repository on GitHub (github.com/JuliusBrussee/caveman) for documentation purposes. As this points to a well-known service, the reference is informative and does not involve automated code execution or risky downloads.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a minimal attack surface as it is designed to output a reference card based on specific user chat triggers.
  • Ingestion points: User-provided chat triggers such as /caveman-help or "caveman help".
  • Boundary markers: None present.
  • Capability inventory: No dangerous capabilities (such as network access, file writing, or shell command execution) are defined or utilized by the skill.
  • Sanitization: Not applicable given the lack of executable actions or data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:30 AM
Security Audit — agent-trust-hub — caveman-help