jb-skill-prefs

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill retrieves configuration data and installation workflows from the author's own GitHub Gist (gist.github.com/bjesuiter). These resources are central to the skill's documented purpose of managing a shared registry.
  • [COMMAND_EXECUTION]: Utilizes the gh command-line tool for Gist synchronization (view, list, create, edit) and npx to run the json5 utility for data validation. These operations are consistent with the skill's role as a registry editor.
  • [PROMPT_INJECTION]: The skill ingests remote instructions from a Gist file (jb-skill-preferences-setup.md) which guide the agent during installation tasks.
  • Ingestion points: Data is read via the gh gist view command as described in the installation and reading sections of SKILL.md.
  • Boundary markers: Remote content is not wrapped in explicit delimiters or ignore-instructions warnings.
  • Capability inventory: The skill can perform shell operations through the gh CLI and execute npm packages via npx.
  • Sanitization: The skill validates the registry's JSON5 syntax but does not perform sanitization of the natural language instructions found in the setup workflow document.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 08:00 PM
Security Audit — agent-trust-hub — jb-skill-prefs