worldlabs

Pass

Audited by Gen Agent Trust Hub on Oct 23, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied data to generate 3D content.
  • Ingestion points: The skill accepts a 'prompt' and 'image path/url' via command-line arguments in SKILL.md.
  • Boundary markers: No delimiters or specific instructions to ignore embedded commands are present in the documentation or CLI examples.
  • Capability inventory: The skill executes shell commands via 'node scripts/worldlabs-generate.mjs' and performs network operations to 'api.worldlabs.ai'.
  • Sanitization: There is no evidence of input validation or sanitization for the user-provided prompts or image sources in the instructions.- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the '@sparkjsdev/spark' npm package and references dependencies from 'sparkjs.dev' and 'cdnjs.cloudflare.com' for 3D rendering functionality.- [COMMAND_EXECUTION]: The skill provides templates for executing a local script 'scripts/worldlabs-generate.mjs' using Node.js to communicate with external APIs and manage generated assets.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 23, 2026, 12:31 PM