matlab-build-toolbox

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's operations are strictly aligned with its stated purpose of build automation and artifact verification. It is provided by a trusted author and uses standard MATLAB environment tools.
  • [COMMAND_EXECUTION]: The skill uses the evaluate_matlab_code tool to invoke the matlab.buildtool.Plan.load and buildtool commands. This is the intended function of a build executor and is restricted to the local project context.
  • [PROMPT_INJECTION]: The skill ingests a local buildfile.m to determine its execution chain. While this represents a surface for indirect instructions, the skill handles it as a structured build plan within the MATLAB ecosystem. 1. Ingestion points: buildfile.m at the project root. 2. Boundary markers: Absent. 3. Capability inventory: evaluate_matlab_code tool. 4. Sanitization: Absent; the skill performs mechanical execution of the loaded plan.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 05:49 PM
Security Audit — agent-trust-hub — matlab-build-toolbox