skills/garrytan/gbrain/schema-author/Gen Agent Trust Hub

schema-author

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes several local command-line interface (CLI) tools, specifically gbrain and git. These are used to query schema status, apply mutations to configuration files, and manage version control for schema packs. This execution is consistent with the skill's stated purpose of authoring and managing technical configurations.
  • [DATA_EXFILTRATION]: The workflow includes a 'Commit' phase that uses git push to upload schema configuration files (pack.json) to a remote repository. This is a standard operation for maintaining configuration history and enabling collaboration, rather than an unauthorized data transfer.
  • [INDIRECT_PROMPT_INJECTION]: The 'Propose' phase (specifically gbrain schema suggest) involves processing the user's existing document corpus to identify potential new schema types. This creates a standard surface for indirect prompt injection where malicious content within the analyzed documents could attempt to influence the naming or structure of suggested schema types, though the impact is restricted to schema metadata configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 04:43 AM
Security Audit — agent-trust-hub — schema-author