livekit-cli
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions to install the LiveKit CLI by fetching and executing a script from the official LiveKit domain (https://get.livekit.io/cli) via a shell pipe. This is a standard installation procedure for the service.
- [INDIRECT_PROMPT_INJECTION]: The skill uses MCP tools to fetch documentation and code examples from external sources, which creates a potential surface for untrusted content to be ingested into the agent's context.
- Ingestion points: Documentation search results and code examples fetched via MCP tools (SKILL.md).
- Boundary markers: No specific delimiters or warnings for the agent to ignore instructions within the fetched documentation are provided.
- Capability inventory: The agent can execute CLI commands, manage project secrets, and deploy infrastructure (references/agent-commands.md).
- Sanitization: No specific sanitization of external documentation content is mentioned in the skill instructions.
- [COMMAND_EXECUTION]: The skill involves the execution of various 'lk' CLI commands for managing resources and deploying agents to the LiveKit Cloud platform.
Audit Metadata