brain-taxonomist
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to utilize local CLI tools, specifically
gbrainandjq, to retrieve schema configurations and perform taxonomy audits. These commands are used to ensure that document filing matches the user's active configuration and are consistent with the vendor's toolset. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided document content to identify the primary subject type for classification.
- Ingestion points: Document content provided to the agent for filing (referenced in the 'Decision Protocol' in SKILL.md).
- Boundary markers: The instructions do not specify explicit delimiters or 'ignore' instructions for the data being analyzed.
- Capability inventory: The skill is authorized to execute the
gbraincommand-line utility for schema lookups and linting. - Sanitization: No explicit sanitization or filtering steps are defined for the input content during the classification process.
Audit Metadata