skills/luxonis/skills/luxonis-model/Gen Agent Trust Hub

luxonis-model

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves documentation and configuration from official vendor-controlled domains, including docs.luxonis.com and mcp.luxonis.com. These are identified as legitimate resources provided by the skill author.
  • [COMMAND_EXECUTION]: The skill uses local command-line tools such as oakctl and the included scripts/validate_nn_archive.py for model validation. These operations are essential to its primary purpose of model integration.
  • [DATA_EXFILTRATION]: The instructions include security guardrails that explicitly require user consent before uploading data to the cloud or using environment-stored credentials like HUBAI_API_KEY.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests information from local project documentation and neural network archive metadata. This data is processed using structured validation scripts to ensure consistency before application integration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 01:16 AM
Security Audit — agent-trust-hub — luxonis-model