lark-vc-agent
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted real-time data from meeting participants.
- Ingestion points: Real-time meeting events such as
chat_received(user chat messages),transcript_received(live speech-to-text), andmagic_share_started(shared document titles and content) are ingested from the+meeting-eventscommand. - Boundary markers: The instructions lack specific requirements for using delimiters or boundary markers to isolate meeting content from the agent's core instructions.
- Capability inventory: The skill has the ability to join and leave meetings (
+meeting-join,+meeting-leave) and is instructed to read external shared documents identified during the meeting. - Sanitization: There are no documented sanitization or filtering steps for the text content ingested from meeting events or shared documents.
- [COMMAND_EXECUTION]: The skill utilizes the
lark-clicommand-line tool to perform conference management. These operations (joining, leaving, and fetching events) are consistent with the skill's stated purpose and are performed using the vendor's official utility.
Audit Metadata