lark-mcp
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references the official
@larksuiteoapi/lark-mcppackage for its core functionality. This is the standard distribution method for the Lark MCP integration and targets an established service organization.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses the capability to ingest and process data from external sources such as Lark documents and chat messages.\n - Ingestion points: Tools like
docx_v1_document_rawContentandim_v1_message_listread external text content into the agent's context.\n - Boundary markers: The skill documentation provides structured templates and core rules to help the agent distinguish between instructions and data content.\n
- Capability inventory: The skill can perform actions like sending messages, creating records, and managing groups, which are the primary intended functions.\n
- Sanitization: The instructions emphasize the use of specific JSON formats for message content and structured field values for Bitable operations, which helps in safe data handling.
Audit Metadata