simulink-run-real-time-application
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill generates MATLAB code to perform operations such as building real-time applications (
slbuild), deploying to targets (install,load), and controlling execution (start,stop). These are standard operations for the intended use case. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes external data from Parquet files and timeseries objects for stimulation and parameter tuning.
- Ingestion points: Data enters through the
reloadDatamethod in thetg.StimulationAPI and throughloadParamSetfor parameter group updates. - Boundary markers: The skill relies on the underlying MATLAB runtime to validate the structure and types of the ingested data.
- Capability inventory: The skill can execute builds, start/stop applications, and modify block parameters on the target hardware.
- Sanitization: The documentation explicitly instructs the agent to verify data dimensions and types against the application's recorded metadata before ingestion, reducing the risk of processing malformed or malicious inputs.
Audit Metadata