subsystem-info

Pass

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill represents an indirect prompt injection surface because it reads and processes external XML data from 1C configuration exports.
  • Ingestion points: XML files are read via the SubsystemPath parameter in scripts/subsystem-info.ps1 and scripts/subsystem-info.py.
  • Boundary markers: No explicit delimiters or instructions are used to isolate the tool's output from the agent's internal instructions.
  • Capability inventory: The scripts have the capability to read local files and optionally write analysis results back to the filesystem.
  • Sanitization: The scripts extract text content from XML elements without specific sanitization or filtering for potential prompt injection content.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 17, 2026, 02:58 PM
Security Audit — agent-trust-hub — subsystem-info