worldlabs
Pass
Audited by Gen Agent Trust Hub on Mar 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the user or agent to execute a local Node.js script
scripts/worldlabs-generate.mjsto perform API interactions and file management. - [EXTERNAL_DOWNLOADS]: The skill connects to
api.worldlabs.aito send generation requests and download 3D assets such as Gaussian Splats and GLB meshes. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection.
- Ingestion points: User-provided text descriptions and image URLs/paths are ingested via the CLI arguments in
SKILL.md. - Boundary markers: No delimiters or instructions to ignore embedded commands are present in the provided documentation.
- Capability inventory: The skill executes a local script (
scripts/worldlabs-generate.mjs) that performs network requests and writes files to the local disk. - Sanitization: There is no evidence of input validation or sanitization for the user-provided prompts or image sources.
Audit Metadata