feishu-im-read
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a documentation guide for interacting with Feishu (Lark) IM APIs. It includes instructions for fetching chat history, searching messages, and downloading media resources using standard Feishu identifiers (chat_id, open_id, file_key).
- [DATA_EXPOSURE]: The skill's primary function is to access sensitive communication data. However, all operations are performed under the user's own identity and permissions, which is consistent with the intended use case of an IM integration.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources (Feishu messages).
- Ingestion points: Tools like
feishu_im_user_get_messagesandfeishu_im_user_search_messagesbring message content into the agent's context. - Boundary markers: The instructions do not define specific delimiters or warnings for the agent to ignore instructions embedded within the fetched messages.
- Capability inventory: No dangerous capabilities (such as shell execution or external network POST requests) are defined within this skill file.
- Sanitization: There are no explicit sanitization or filtering steps mentioned for the retrieved message content.
Audit Metadata