Skills
Navigate
skills/nikolay-shirokov/cc-1c-skills/role-info/Gen Agent Trust Hub

role-info

Pass

Audited by Gen Agent Trust Hub on Oct 27, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external 1C configuration files which creates an indirect prompt injection surface.
  • Ingestion points: The scripts role-info.ps1 and role-info.py read Rights.xml, metadata files, and ParentConfigurations.bin based on user-provided paths.
  • Boundary markers: The skill does not implement delimiters or ignore-instructions warnings for the data processed and presented to the agent.
  • Capability inventory: The skill allows reading local files and writing output to a user-specified file path via the -OutFile parameter.
  • Sanitization: The tool performs structured XML parsing but does not sanitize or filter potential natural language instructions within the data.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of local utility scripts using powershell.exe and python3, accepting file paths as arguments.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 27, 2026, 05:16 PM