xq

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes scripts and instructions to download and install jq and yq (which provides the xq utility). These downloads target official and well-known repositories including GitHub, PyPI, and standard OS package managers such as Homebrew, APT, and Winget.
  • [COMMAND_EXECUTION]: Provides templates and shell scripts for system-level operations such as package installation and XML data transformation using CLI tools.
  • [PROMPT_INJECTION]: While the skill is designed to process external XML data, it includes markers and security notes emphasizing that XXE (XML External Entity) expansion is disabled by default via the underlying xmltodict library.
  • Ingestion points: Processes external XML files and streams via standard input in files like SKILL.md and references/advanced-usage.md.
  • Boundary markers: Uses standard shell piping and argument structures to isolate data from logic.
  • Capability inventory: Accesses the file system for reading XML and performs subprocess execution for xq, jq, and xmllint transformations.
  • Sanitization: Relies on the security configurations of the underlying yq (Python) package and xmltodict library to prevent entity injection and other XML-based attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 04:18 PM
Security Audit — agent-trust-hub — xq