matlab-analyze-rcs

Pass

Audited by Gen Agent Trust Hub on Jul 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the mcp__matlab__evaluate_matlab_code tool to execute MATLAB scripts. This is the intended functional mechanism for performing RCS calculations and generating plots.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where user-supplied data (such as filenames for STL/MAT files and frequency values) is interpolated into MATLAB code blocks.
  • Ingestion points: File paths and frequency parameters provided by the user.
  • Boundary markers: Absent; user input is placed directly into code strings.
  • Capability inventory: High-privilege code execution via the evaluate_matlab_code tool.
  • Sanitization: The instructions do not specify input validation or escaping for the user-provided strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 18, 2026, 07:42 PM
Security Audit — agent-trust-hub — matlab-analyze-rcs