feishu-channel
Pass
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Communicates with
open.feishu.cn, the official API domain for Feishu/Lark, which is a well-known service. - [PROMPT_INJECTION]: The skill acts as an ingestion point for untrusted user input from the Feishu platform, creating an indirect prompt injection surface.
- Ingestion points: The webhook server in
scripts/feishu-webhook.jsreceives message content from external users via the/webhook/feishuendpoint. - Boundary markers: The current implementation does not use explicit prompt delimiters or "ignore embedded instructions" warnings when forwarding user text.
- Capability inventory: The skill performs network operations in
scripts/feishu-webhook.jsand requests access toBash,Read,Write, andEdittools inSKILL.md. - Sanitization: It implements security controls such as
ALLOWED_USERSandALLOWED_GROUPSfilters to restrict interaction, and includes a mention requirement for group chats.
Audit Metadata