lark-cli
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed around the execution of the
lark-clibinary to manage workspace operations including calendar, documents, mail, and IM messages. - [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest and process data from external, potentially untrusted workspace sources.
- Ingestion points: Documents, sheets, wiki pages, drive files, and real-time messages retrieved via
lark-clifrom the Feishu/Lark environment. - Boundary markers: The instructions lack explicit delimiters or warnings to treat workspace data as untrusted content.
- Capability inventory: The agent can perform read and write operations (including
high-risk-write) across 23 different workspace domains. - Sanitization: No sanitization or validation mechanisms are described for the content fetched by the CLI before it is processed by the agent.
Audit Metadata