add-webgpu-canvas

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the well-known libraries '@react-three/fiber' and 'three' from the official npm registry.
  • [COMMAND_EXECUTION]: The workflow requires running 'npm install' to manage dependencies and executing project-specific build or type-check scripts to verify the integration.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from the target repository which represents a potential attack surface.
  • Ingestion points: Reads local instructions and file structures from the target repository to determine integration steps.
  • Boundary markers: No delimiters are specified to separate external repository content from the agent's instructions.
  • Capability inventory: The skill has the ability to write components to the file system, install packages via npm, and execute shell commands for build verification.
  • Sanitization: No sanitization or validation of the ingested repository content is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 08:10 AM
Security Audit — agent-trust-hub — add-webgpu-canvas