documint
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the Membrane CLI tool (
@membranehq/cli) from the npm registry. This is a vendor-owned package necessary for the skill's integration logic. - [COMMAND_EXECUTION]: The skill utilizes the
membranecommand-line interface to execute various operations including authentication (membrane login), connection management (membrane connect), and running Documint actions. These commands are integral to the documented functionality. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it retrieves and processes data from Documint templates and documents. 1. Ingestion points: Data enters the context via
membrane action runandmembrane request(SKILL.md). 2. Boundary markers: No specific delimiters or instructions to ignore embedded content are present. 3. Capability inventory: The skill uses subprocess calls to themembraneCLI (SKILL.md). 4. Sanitization: No explicit sanitization or validation of the retrieved document content is documented.
Audit Metadata