lark-im
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves retrieving and processing untrusted data from external chat participants.
- Ingestion points: The agent can fetch external content through message listing (+chat-messages-list), cross-chat search (+messages-search), and by listening for card interaction events (card.action.trigger).
- Boundary markers: The documentation does not specify the use of clear delimiters or instructions to ignore potential commands embedded within retrieved chat data when passed to the agent's context.
- Capability inventory: The skill possesses significant capabilities, including sending messages and interactive cards (+messages-send, +messages-reply), modifying chat settings, managing group membership, and writing files to the local system via resource downloads.
- Sanitization: The tool implements proactive security measures for file operations; the +messages-resources-download command restricts output to specific allowed directories and validates paths to prevent directory traversal attacks.
Audit Metadata