The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses evaluate_matlab_code to interact with the MATLAB environment. It also provides APIs like setCallback and setColumnFormula that allow for the definition of MATLAB code strings to be stored and executed as callbacks or formulas within Safety Analysis Manager documents.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data from external files and models. 1. Ingestion points: Data enters the agent context through model_read, safetyAnalysisMgr.openDocument, and safetyAnalysisMgr.import. 2. Boundary markers: Instructions emphasize grounding the analysis in the actual model structure or requirements text. 3. Capability inventory: The skill can execute MATLAB commands via evaluate_matlab_code and perform file writes via save and export functions. 4. Sanitization: No explicit sanitization of ingested content is described in the provided files.
[SAFE]: The skill includes a pre-compiled MATLAB P-code script (scripts/fileType.p) for document type verification. This is a standard vendor-authored helper script and is considered a legitimate component of the skill's functionality.

manage-safety-analysis