simulink-customize-a2l
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes Simulink model files and external symbol mapping files which could contain malicious data designed to influence agent behavior.
- Ingestion points: The workflow relies on loading system models via
load_system(modelName)and supports reading external symbol files (ELF, PDB, DWARF) through theMapFileproperty documented inreferences/construction-time-properties.md. - Boundary markers: There are no specific delimiters or instruction-ignoring warnings configured for the ingestion of these external data sources.
- Capability inventory: The skill possesses significant capabilities including the execution of arbitrary MATLAB logic via
evaluate_matlab_codeand the ability to write files to the local file system through thecoder.asap2.exportAPI. - Sanitization: The instructions lack guidance on validating or sanitizing the content of the ingested models or mapping files before they are processed by the agent.
Audit Metadata