ovrtx-lidar-runtime-capture

Pass

Audited by Gen Agent Trust Hub on Aug 22, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow for processing external sensor schemas and raw return data, creating a potential surface for indirect prompt injection if the ingested data contains malicious instructions.
  • Ingestion points: External sensor/product schemas and raw LiDAR return data processed during validation steps.
  • Boundary markers: Not present; the instructions do not specify using delimiters or 'ignore' instructions for the external data.
  • Capability inventory: The agent relies on default environment tools to perform validation, simulation iteration, and artifact creation.
  • Sanitization: No explicit data sanitization or schema validation rules are provided to the agent for handling the untrusted input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 22, 2026, 06:05 PM
Security Audit — agent-trust-hub — ovrtx-lidar-runtime-capture