skills/b-open-io/prompts/shaders/Gen Agent Trust Hub

shaders

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references several well-known and trusted external resources including The Book of Shaders, Shadertoy, LYGIA, and Inigo Quilez's articles. These are standard educational resources for shader development and do not represent a security risk.
  • [COMMAND_EXECUTION]: Instructions include standard package management commands (bun add) for installing the postprocessing and @react-three/postprocessing libraries. These are established community-standard tools in the Three.js ecosystem.
  • [REMOTE_CODE_EXECUTION]: The skill describes a pattern for resolving shader dependencies at runtime using the resolveLygiaAsync method from lygia.xyz. This is a common practice for integrating the LYGIA shader library to handle module resolution and shader includes.
  • [SAFE]: No prompt injection, data exfiltration, or obfuscation attempts were detected. The skill aligns with its stated purpose of providing technical documentation and snippets for graphics programming.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 03:27 AM