feishu-wiki
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of data from external Wiki nodes, which can be leveraged to deliver malicious instructions to the agent context.
- Ingestion points: Data enters the agent's context through the
GET /spaces/{space_id}/nodes/{node_token}endpoint referenced in the documentation. - Boundary markers: The skill instructions do not define any specific delimiters or instructions to the agent to disregard or escape natural language commands found within the Wiki content.
- Capability inventory: The skill possesses capabilities to write and modify data, including creating new knowledge spaces, creating new nodes, and moving existing nodes via POST requests.
- Sanitization: There is no evidence in the skill definition of any filtering, validation, or sanitization of content returned from the external Feishu API endpoints.
Audit Metadata