lark-skill-maker

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is primarily instructional, providing a standardized template for creating other skills. It does not contain any executable scripts or hidden logic that would compromise the agent or the user's environment.
  • [COMMAND_EXECUTION]: The skill documents patterns for using lark-cli, a tool for interacting with the Lark/Feishu API. The instructions focus on legitimate API exploration and task orchestration within that platform.
  • [PROMPT_INJECTION]: The skill describes a workflow that involves ingesting API documentation (via the lark-openapi-explorer skill) to construct commands. While this creates a potential surface for indirect prompt injection from documentation content, the skill mitigates this by instructing the agent to confirm user intent and utilize --dry-run modes for any data-modifying actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 09:52 AM