matlab-call-nidaqmx

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of MATLAB code based on user-provided strings which are interpolated into commands executed via the toolkit.
  • Ingestion points: User prompts defining hardware configurations and DAQmx function parameters (SKILL.md).
  • Boundary markers: Absent; the instructions do not require the agent to wrap user data in delimiters or include ignore-instruction warnings.
  • Capability inventory: The manifest.yaml allows for the evaluate_matlab_code tool, which executes generated code.
  • Sanitization: Absent; the skill does not instruct the agent to escape or validate user-provided strings before inclusion in code.
  • [DYNAMIC_EXECUTION]: The skill generates calls to calldaqlib, which dynamically invokes functions from the NI-DAQmx driver library. This is the primary intended function of the skill and is used for hardware control.
  • [SAFE]: Analysis of the instructions, metadata, and reference files reveals no evidence of prompt injection, data exfiltration, or persistence mechanisms. The resources and author are associated with a trusted organization.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:27 AM
Security Audit — agent-trust-hub — matlab-call-nidaqmx