livekit
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install the
@membranehq/clipackage globally via npm to interact with the Membrane platform. - [COMMAND_EXECUTION]: The skill relies on executing terminal commands through the
membraneCLI for authentication, connection management, and performing LiveKit actions. - [INDIRECT_PROMPT_INJECTION]: The skill processes real-time communication data (rooms, tracks, and participants) from LiveKit, which could contain untrusted content capable of influencing agent behavior.
- Ingestion points: Data returned from shell commands such as
membrane action runandmembrane request(SKILL.md). - Boundary markers: Absent; there are no instructions to the agent to treat API output as data rather than instructions, nor are there delimiters used.
- Capability inventory: The skill provides capabilities to execute shell commands, manage authenticated connections, and perform network requests (SKILL.md).
- Sanitization: Absent; the skill does not define any validation or escaping for the data fetched from the external API.
Audit Metadata