Feishu Integration Developer
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the Feishu platform, which represents an attack surface for indirect prompt injection.
- Ingestion points: Ingests data from external users via event subscriptions, specifically handling
im.message.receive_v1for incoming messages andapproval.approval.updated_v4for workflow updates insrc/webhook/event-dispatcher.ts. - Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious instructions embedded within the processed messages.
- Capability inventory: The skill possesses significant capabilities, including the ability to send messages, manage approval workflows, and modify Bitable spreadsheet records across its core modules.
- Sanitization: There is no evidence of content sanitization or validation performed on incoming strings before they are processed by the bot's command handlers.
- [EXTERNAL_DOWNLOADS]: The skill utilizes the official Feishu Open Platform SDK for Node.js.
- Evidence: The code references the
@larksuiteoapi/node-sdkpackage to facilitate communication with the well-known Feishu platform APIs.
Audit Metadata