High-risk tools in Session Buddy
15 of the 80 tools in Session Buddy 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
-
chat_with_llmExecuteHave a conversation with an LLM provider.
-
execute_batch_on_poolExecuteExecute multiple tasks in parallel on a pool.
-
execute_on_poolExecuteExecute a task on a specific pool.
-
force_conscious_analysisExecuteForce a one-time analysis run.
-
generate_with_llmExecuteGenerate text using specified LLM provider.
-
invoke_skillExecuteInvoke a learned skill to get workflow guidance.
-
route_to_poolExecuteRoute task to best available pool using specified strategy.
-
startExecuteInitialize Claude session with comprehensive setup including UV dependencies and automation tools.
-
start_app_monitoringExecuteStart monitoring IDE activity and browser documentation usage.
-
start_conscious_agentExecuteStart background Conscious Agent if enabled by flags.
-
start_interruption_monitoringExecuteStart monitoring for interruptions and context switches.
-
stop_app_monitoringExecuteStop all application monitoring.
-
stop_conscious_agentExecuteStop background Conscious Agent if running.
-
stop_interruption_monitoringExecuteStop interruption monitoring.
-
trigger_learningExecuteManually trigger learning from a checkpoint.
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.