xdto-compile

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill performs legitimate 1C:Enterprise development tasks.\n- [EXTERNAL_DOWNLOADS]: The skill's scripts reference the author's GitHub repository (github.com/Nikolay-Shirokov/cc-1c-skills). These are neutral references to the vendor's source code and do not involve unauthorized remote code execution.\n- [COMMAND_EXECUTION]: The skill executes local PowerShell and Python scripts to transform XML schemas into 1C metadata. These operations are limited to the user-provided output directory and do not request elevated privileges.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted XSD data through the -XsdPath or -Xsd arguments.\n
  • Ingestion points: XML Schema data is loaded in scripts/xdto-compile.ps1 and scripts/xdto-compile.py.\n
  • Boundary markers: None identified for the ingested XSD content.\n
  • Capability inventory: The scripts write to the local file system (creating XDTOPackages directories and files) and modify the Configuration.xml file.\n
  • Sanitization: The skill uses standard XML libraries for parsing and implements text escaping (EscText) when interpolating data into metadata templates, mitigating the risk of structural injection into the generated XML files.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 10:28 PM
Security Audit — agent-trust-hub — xdto-compile