plc-code-analysis

Pass

Audited by Gen Agent Trust Hub on Oct 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data, creating a surface for indirect prompt injection where malicious instructions could be embedded in the code being reviewed.
  • Ingestion points: The skill reads data from pasted PLC code (SCL/ST), uploaded SIMATIC SD and SimaticML XML files, and context retrieved via MCP tools (block content, tag tables, hardware config) as defined in Format 1-4 in SKILL.md.
  • Boundary markers: The skill instructions emphasize identifying the provenance of input and building a 'context manifest' to track the status and source of every analyzed item, which helps maintain logical boundaries during the analysis.
  • Capability inventory: The skill's primary function is data retrieval and report generation. It utilizes specific MCP tools for PLC project mapping and content retrieval (e.g., browse_project_tree, get_block_content) but does not have the capability to execute shell commands or write to the local file system.
  • Sanitization: There are no explicit instructions to sanitize or escape the content of the PLC code or XML metadata before it is processed by the agent, allowing for potential adversarial influence via comments or data within the audited files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 9, 2026, 05:20 PM