3d-web-experience

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • Unverifiable Dependencies & Remote Code Execution (SAFE): The skill provides instructions for installing well-known, standard development packages such as @splinetool/react-spline and @gltf-transform/cli via npm. These are appropriate for the domain and present no security risk.
  • Command Execution (SAFE): Reference shell commands for asset optimization (e.g., ls -lh, npx) are included as instructional snippets for the user and are not executed autonomously by the agent.
  • Indirect Prompt Injection (SAFE): The skill serves as a static expert reference; it does not process external, untrusted data in a way that creates an injection surface.
  • Prompt Injection (SAFE): The instructions in SKILL.md and reference files are aimed at grounding the agent's expertise and do not attempt to bypass safety filters or override core system instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM