lark-cli
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides the agent with capabilities to ingest and process data from external, untrusted sources within the Lark/Feishu environment, which presents a surface for indirect prompt injection attacks.
- Ingestion points: The skill reads content from IM messages, chat history, cloud documents (Docs, Sheets, Base), and meeting transcripts (SKILL.md).
- Boundary markers: The instructions lack specific guidance on using delimiters or strict 'ignore instructions' warnings when handling content retrieved from these external sources.
- Capability inventory: The skill can perform actions such as sending/replying to messages, creating or editing documents, and managing tasks/permissions, which could be triggered by malicious instructions embedded in the processed data.
- Sanitization: There are no explicit instructions for sanitizing or escaping the external content before it is processed by the agent.
Audit Metadata