feishu-card
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill includes functionality to process external text content for transmission to Feishu. This represents an ingestion surface for potentially untrusted data.
- Ingestion points: Input is received via the
--textCLI flag or by reading from a file with--text-file. - Boundary markers: The documentation instructs on proper escaping and formatting but does not include explicit delimiters for the agent to ignore embedded instructions.
- Capability inventory: The skill triggers a Node.js script to perform network requests to the Feishu Open API.
- Sanitization: Content validation and escaping are expected to be performed by the
send.jsscript referred to in the usage instructions.
Audit Metadata