feishu-im
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local script
./scripts/get_feishu_token.shto retrieve and refresh authentication tokens. - [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied data to construct Feishu messages and group metadata, which could be exploited by malicious inputs.
- Ingestion points: Data enters through message
content, groupname,description, andannouncementfields in SKILL.md. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands when interpolating user data into API requests.
- Capability inventory: The skill possesses the ability to send network requests to the Feishu API to post messages, create/delete chats, and modify group memberships.
- Sanitization: The instructions do not specify any validation or sanitization routines for the data before it is sent to the external API.
Audit Metadata