add-shader-cursor-trail

Pass

Audited by Gen Agent Trust Hub on Nov 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user or agent to execute a local Node.js utility, scripts/verify-cursor-trail.mjs, for validating implementation files.
  • [INDIRECT_PROMPT_INJECTION]: The verify-cursor-trail.mjs script reads file contents from the local filesystem based on command-line arguments, creating a potential surface for reading unauthorized files.
  • Ingestion points: File paths provided to the verify-cursor-trail.mjs script as arguments in SKILL.md.
  • Boundary markers: Absent; the script does not include explicit warnings to ignore embedded instructions in the files it reads.
  • Capability inventory: The script uses node:fs/promises to read files and performs regex-based validation.
  • Sanitization: The script only checks for specific patterns and throws an error on failure without outputting the file content, which significantly reduces the risk of data exposure.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the shaders package (e.g., shaders/react) through a package manager to provide the WebGPU components and shader nodes.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 11, 2026, 04:45 PM