glb-compressor-server

Pass

Audited by Gen Agent Trust Hub on Feb 20, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION] (LOW): The server documentation indicates the use of external binaries like gltfpack and meshopt for compression. This pattern implies a potential command injection surface if the implementation fails to properly sanitize user-provided parameters such as 'preset' and 'simplify' before invoking shell commands.
  • [INDIRECT_PROMPT_INJECTION] (LOW): The skill documentation outlines a service that ingests untrusted GLB/glTF data, which could contain malicious instructions for an LLM if the output is consumed by an agent. 1. Ingestion points: /compress and /compress-stream endpoints. 2. Boundary markers: No delimiters or instruction-ignore warnings are mentioned in the documentation. 3. Capability inventory: System execution of compression tools. 4. Sanitization: Only magic-byte validation (INVALID_GLB) is documented, with no mention of sanitizing internal 3D model metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 20, 2026, 11:32 PM