Skills
skills/membranedev/application-skills/docsumo/Gen Agent Trust Hub

docsumo

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the @membranehq/cli package from the NPM registry to facilitate platform interactions.
  • [COMMAND_EXECUTION]: Executes terminal commands via the membrane CLI for user authentication, connection setup, and API action execution.
  • [PROMPT_INJECTION]: Surface for indirect prompt injection through document data processing. Ingestion points: get-extracted-data, get-document-details, and list-documents. Boundary markers: None identified. Capability inventory: File deletion (delete-document), status updates (update-review-status), and arbitrary API proxying (membrane request). Sanitization: None identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 10:29 PM