shipperhq

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to install the @membranehq/cli package globally via NPM. This is a legitimate utility provided by the vendor to facilitate the integration.
  • [COMMAND_EXECUTION]: Employs the membrane command-line interface for lifecycle operations such as authentication (membrane login), connection discovery (membrane connection list), and action execution (membrane action run).
  • [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it retrieves data from external ShipperHQ API endpoints that is then processed by the agent.
  • Ingestion points: Output from API requests executed via membrane action run and membrane request (SKILL.md).
  • Boundary markers: Absent; the instructions do not specify delimiters or warnings for the agent to ignore instructions embedded in the API data.
  • Capability inventory: The skill can execute CLI commands, perform network requests via a proxy, and list system connections (SKILL.md).
  • Sanitization: No explicit sanitization or validation of the external API response content is described in the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 08:51 PM