lark-calendar
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for managing Lark Calendar using the
lark-clitool. It supports creating, updating, and searching for calendar events and participant availability. All operations are consistent with the primary use case and no indicators of credential harvesting or data exfiltration to unauthorized third parties were found. - [COMMAND_EXECUTION]: The skill relies on the
lark-clibinary to interact with the Lark platform. It also recommends using system tools for precise date and time calculations. This behavior is expected and safe within the scope of an enterprise calendar integration. - [PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection via user-provided text.
- Ingestion points: The
summaryanddescriptionfields used in the+createshortcut andevents.createAPI call (specified in SKILL.md and lark-calendar-create.md). - Boundary markers: Content is separated using CLI flags, but there are no explicit delimiters or instructions to the agent to treat input as untrusted data.
- Capability inventory: The agent can manage (create, list, delete) calendar events and check user busy/free status.
- Sanitization: No documentation exists within the skill instructions regarding input sanitization or validation.
Audit Metadata