feishu-cli-data
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill relies on executing the feishu-cli and jq binaries to interact with Feishu APIs and process complex JSON structures.
- [CREDENTIALS_UNSAFE]: The instructions cover the management of sensitive Feishu credentials, such as app secrets and user access tokens, including references to local token storage in ~/.feishu-cli/token.json and usage via environment variables.
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it retrieves data from external Feishu spreadsheets and tables that could contain instructions intended to influence agent behavior.
- Ingestion points: External data is ingested through commands like feishu-cli sheet read and feishu-cli bitable record list.
- Boundary markers: The instructions do not define specific delimiters to separate user data from instructions.
- Capability inventory: The execution environment provides access to shell commands (feishu-cli, jq) and filesystem operations (Read, Write).
- Sanitization: No data sanitization steps are documented for processing content from external spreadsheet cells.
Audit Metadata