matlab-connect-opcua-client

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/inspectOpcUaCertificate.m invokes shell commands via the MATLAB system() function to utilize openssl for certificate analysis. While the certFile argument is validated using the {mustBeFile} attribute to ensure the target exists, the use of string interpolation (sprintf) to construct the shell command presents a potential command injection vulnerability on operating systems that allow shell metacharacters in filenames.
  • [PROMPT_INJECTION]: The skill facilitates the ingestion and processing of external data from OPC UA certificates, creating an indirect prompt injection surface.
  • Ingestion points: The scripts/inspectOpcUaCertificate.m script reads and extracts fields from .der and .pem certificate files.
  • Boundary markers: Absent; the output of the inspection script is provided to the agent without specific delimiters or instructions to ignore embedded content.
  • Capability inventory: The skill possesses the ability to perform filesystem operations (mkdir, copyfile, rmdir) and execute shell commands (system) through the evaluate_matlab_code tool.
  • Sanitization: Absent; the script extracts certificate metadata using regular expressions but does not sanitize the resulting strings before they are returned to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:27 AM
Security Audit — agent-trust-hub — matlab-connect-opcua-client