matlab-find-pi-assets

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious code or suspicious patterns were detected. The skill follows secure design principles by requiring explicit user consent for network connections and server selection.
  • [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests data from external PI systems. Ingestion points: Data is retrieved via read, readHistory, and tags functions in SKILL.md. Boundary markers: Absent. Capability inventory: Uses evaluate_matlab_code (manifest.yaml) for MATLAB execution. Sanitization: No explicit data sanitization is performed. This surface is characteristic of data retrieval tools and is considered safe in this context.
  • [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were found. The skill does not access sensitive local configuration files or hardcoded credentials.
  • [COMMAND_EXECUTION]: The skill generates MATLAB code for execution through the platform's standard tools. This behavior is restricted to the MATLAB environment and is the intended primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:14 AM
Security Audit — agent-trust-hub — matlab-find-pi-assets