feishu-cli-data
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading data from external Feishu documents (Spreadsheets and Bitables), which creates a surface for indirect prompt injection if those documents contain malicious instructions. * Ingestion points: Data is ingested through commands like 'sheet read' and 'record list' as described in the reference documentation files. * Boundary markers: The skill instructions do not specify the use of delimiters or 'ignore' instructions to isolate untrusted data retrieved from Feishu. * Capability inventory: The skill utilizes 'Bash' (to execute feishu-cli and jq), along with 'Read' and 'Write' tools, enabling the agent to perform networked operations and local file access. * Sanitization: There are no specific instructions for validating or sanitizing external content before it is processed by the agent or included in future prompts.
Audit Metadata