High-risk tools in WISE-Agent
14 of the 378 tools in WISE-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
-
blender_batch_transformExecuteBatch transform matching objects.
-
blender_collab_hostExecuteStart a collaboration session as host
-
blender_execute_pythonExecuteExecute Python code in Blender.
-
blender_object_transformExecuteTransform an object (location, rotation, scale).
-
blender_quality_audit_fullExecuteRun topology + UV + performance triple audit and output a combined score.
-
blender_quality_audit_performanceExecuteAudit performance budget (triangles, material slots, estimated draw calls).
-
blender_sculpt_strokeExecuteExecute a sculpt stroke
-
blender_texture_paint_strokeExecuteExecute a texture paint stroke
-
blender_training_run_commandExecuteExecute a predefined MCP command from an exercise. Directly performs operations in Blender to help learners understand tool usage.
-
blender_training_start_exerciseExecuteStart an exercise. Returns first step guidance and available MCP commands.
-
blender_uv_transformExecuteTransform UV coordinates.
-
blender_vr_preview_startExecuteStart VR preview
-
blender_vr_preview_stopExecuteStop VR preview
-
blender_vse_transformExecuteTransform a video strip (position, scale, rotation, opacity).
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.