skills/pixazo-ai/skills/hyper3d/Gen Agent Trust Hub

hyper3d

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill manages a Pixazo API key by checking environment variables and the local path ~/.pixazo/api-key. It correctly instructs the agent to save user-provided keys with restricted permissions (chmod 600), adhering to security best practices.
  • [EXTERNAL_DOWNLOADS]: The skill directs the agent to fetch model-specific configuration and documentation from the vendor's domain at https://www.pixazo.ai/models/hyper3d.md.
  • [COMMAND_EXECUTION]: The documentation mentions an npx command for installing related skills from the Pixazo-AI organization as a reference for users.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user prompts and API response data.
  • Ingestion points: User prompts and task status responses from the Pixazo gateway.
  • Boundary markers: No specific boundary markers are defined for the prompt interpolation.
  • Capability inventory: File writes to ~/.pixazo/, chmod commands, and network operations using curl, Python requests, and Node.js fetch.
  • Sanitization: The instructions do not specify sanitization for user-provided strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 09:02 PM