lark-workflow-meeting-todo
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the lark-cli binary to perform extensive operations including searching meetings, fetching document content, sending messages, and creating tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from meeting notes and documents to extract task information. This presents a vulnerability surface where malicious instructions in a meeting note could attempt to influence agent behavior, although the risk is mitigated by a mandatory human confirmation step.
- [EXTERNAL_DOWNLOADS]: The skill specifies a dependency on the lark-cli binary in its metadata frontmatter requirements.
Audit Metadata