threejs-choose-skills

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as a purely instructional framework for task routing within the Three.js ecosystem. It does not contain any executable scripts, binary files, or network-enabled commands.
  • [NO_CODE]: The skill package is composed entirely of Markdown documentation and YAML configuration files. It lacks scripts (Python, JavaScript, shell) that could facilitate automated malicious actions.
  • [DATA_EXFILTRATION]: No network operations (e.g., curl, wget) or sensitive file path references (e.g., .ssh, .aws, .env) were found. The skill only references local documentation files within its own package.
  • [PROMPT_INJECTION]: The instructions are strictly technical and oriented toward 3D rendering workflows. There are no attempts to override agent safety protocols, exfiltrate system prompts, or bypass ethical constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 07:20 PM
Security Audit — agent-trust-hub — threejs-choose-skills