High-risk tools in Live2d To Agent
6 of the 11 tools in Live2d To Agent are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
action_performExecute播放 Live2D 角色的语义动作。可用动作：
-
expression_setExecute切换 Live2D 角色的表情。根据对话情绪选择合适的表情。
-
live2d_expressionExecute切换 Live2D 表情。从模型定义的表情中选择。
-
live2d_motionExecute播放 Live2D 动作组。从模型定义的动作组中选择。
-
live2d_parameterExecute直接操控 Live2D 底层参数。参数 ID 因模型而异，通过 live2d_status 获取可用参数。
-
model_loadExecute加载 Live2D 模型。指定包含 .model3.json 的目录路径，
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.