lark-minutes
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
lark-clibinary to interact with official Lark API resources. These commands are localized to the platform's functionality for fetching meeting summaries and metadata. - [DATA_EXFILTRATION]: There are no indicators of data being sent to non-vendor domains. The operations are restricted to the Feishu/Lark ecosystem (
feishu.cn) using designatedminute_tokenidentifiers. - [PROMPT_INJECTION]: The instructions are purely functional and do not contain attempts to override agent constraints, ignore safety guidelines, or extract system prompts.
- [EXTERNAL_DOWNLOADS]: No external scripts or untrusted dependencies are downloaded at runtime. The skill relies on the pre-installed
lark-clias specified in the metadata.
Audit Metadata