onna

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official @membranehq/cli tool from the NPM registry to facilitate communication with the Membrane platform.
  • [COMMAND_EXECUTION]: Utilizes the membrane command-line interface to perform operations such as logging in, connecting to services, and executing workflow actions.
  • [PROMPT_INJECTION]: Processes data retrieved from external Onna sources such as Slack or Google Drive, which represents an indirect ingestion surface.
  • Ingestion points: Search results and action outputs retrieved via the CLI (SKILL.md).
  • Boundary markers: Not explicitly specified in the instructions.
  • Capability inventory: Executes shell commands via the Membrane CLI (SKILL.md).
  • Sanitization: Relies on the Membrane platform's structured data handling and API abstraction for external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:59 AM
Security Audit — agent-trust-hub — onna