lark-im
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes untrusted data from Feishu chat messages using tools like +chat-messages-list and +messages-search. Ingestion points: Message retrieval shortcuts in SKILL.md and related reference files. Boundary markers: The instructions do not define delimiters or specific warnings for untrusted message content. Capability inventory: Message sending, group management, and card update operations via lark-cli. Sanitization: No specific sanitization of chat message content is mandated before processing.
Audit Metadata