drata

Pass

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli package via npm. This is the official command-line interface provided by the vendor for managing integrations.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform operations such as authentication, connection setup, and action execution. These commands are standard for the intended functionality of the skill.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from the Drata API (e.g., policy descriptions, user metadata, asset records).
  • Ingestion points: Data enters the agent context through CLI commands like membrane action run and membrane request (SKILL.md).
  • Boundary markers: No explicit instructions are provided to the agent to treat external Drata data as untrusted or to use specific delimiters.
  • Capability inventory: The skill has the capability to execute shell commands via the Membrane CLI and make arbitrary network requests through the proxy tool (SKILL.md).
  • Sanitization: There are no documented sanitization or escaping steps for the data retrieved from the external API.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 19, 2026, 05:48 PM