matlab-simulate-radar-detections

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is designed to parse untrusted user data, specifically radar hardware datasheets and performance requirements, as described in Step 3 of the workflow and the 'Datasheet Ingestion' section of references/coupled-parameters.md. This data is used to parameterize and generate MATLAB simulation code. The absence of explicit boundary markers or sanitization instructions for this external content creates a surface for indirect prompt injection.
  • Ingestion points: User-provided radar datasheets and hardware specifications (SKILL.md, references/coupled-parameters.md).
  • Boundary markers: Absent from the instructions.
  • Capability inventory: Code generation and execution via evaluate_matlab_code and run_matlab_file (manifest.yaml).
  • Sanitization: No validation or content escaping for the extracted technical text is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 11:14 AM
Security Audit — agent-trust-hub — matlab-simulate-radar-detections