help-scout

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the Membrane CLI from the npm registry using the vendor's official package scope (@membranehq/cli).
  • [COMMAND_EXECUTION]: Uses subprocess calls to the membrane CLI for authentication, connection management, and executing Help Scout actions.
  • [PROMPT_INJECTION]: Contains a vulnerability surface for indirect prompt injection when handling external data. * Ingestion points: Conversation and article data retrieved from Help Scout via the membrane action run command. * Boundary markers: The skill lacks delimiters or explicit instructions to the agent to ignore commands embedded within retrieved customer data. * Capability inventory: Includes capabilities to execute diverse API actions and generate new actions through the membrane CLI. * Sanitization: No sanitization or validation of external content is specified before the data is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:59 AM
Security Audit — agent-trust-hub — help-scout