ringcentral
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs users to install the '@membranehq/cli' package globally using npm. This package is an official tool from the skill vendor (membranedev) used to manage connections and execute API actions.- [COMMAND_EXECUTION]: Integration logic is implemented through local execution of the 'membrane' CLI tool to perform authentication, search for connectors, and run specific actions against the RingCentral API.- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface. It ingests untrusted data from RingCentral (e.g., through 'list-messages' and 'list-chats' in SKILL.md) without explicit boundary markers or sanitization. If the agent processes this content and subsequently uses its capabilities (like 'membrane action run' or 'membrane request' in SKILL.md) based on instructions hidden within that data, it could lead to unintended behavior.
Audit Metadata