plc-code-analysis

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a security auditing tool designed to detect vulnerabilities in PLC code. All documented patterns and 'suspicious' indicators (e.g., date-based triggers, memory manipulation, and communication bypasses) are categorized as checklist items for the agent to find in user-provided code, rather than behaviors the agent itself performs.
  • [COMMAND_EXECUTION]: The skill utilizes a set of MCP (Model Context Protocol) tools (get_block_content, read_hardware_config, compile_check, etc.) specifically designed to interact with Siemens TIA Portal engineering environments. These tools are scoped to the intended purpose of retrieving code for analysis and do not provide generalized shell access.
  • [DATA_EXFILTRATION]: The skill processes sensitive engineering data (PLC logic, hardware configurations, and network settings). Analysis confirms this data is used locally within the agent's context to generate a security report and is not transmitted to unauthorized external domains.
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes untrusted user-provided PLC code and SimaticML XML files (Category 8).
  • Ingestion points: Raw SCL/Structured Text inputs and SimaticML XML file uploads (defined in SKILL.md).
  • Boundary markers: Not explicitly defined in the interpolation instructions.
  • Capability inventory: MCP tools scoped to project tree browsing, block retrieval, hardware configuration reading, and compilation checking.
  • Sanitization: None specified for input data; however, the risk is mitigated by the skill's constrained purpose of generating static analysis reports rather than executing logic in the engineering system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 07:55 AM
Security Audit — agent-trust-hub — plc-code-analysis