High-risk tools in Neuron
12 of the 231 tools in Neuron 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
-
neuron_bot_api_chatExecuteSend a message to a bot via the API and receive a streaming or complete AI-generated response. Requires a valid API key with 'nrn_' prefix.
-
neuron_pause_botExecutePause a bot to temporarily stop it from processing new messages. The bot retains its configuration and can be resumed later.
-
neuron_refresh_contact_listExecuteTrigger a refresh of a dynamic contact list. Re-evaluates criteria rules and/or AI prompt and materializes updated members.
-
neuron_request_pair_codeExecuteRequest a numeric pairing code for a Baileys channel as an alternative to QR code scanning. Requires the phone number to pair with.
-
neuron_resume_botExecuteResume a previously paused bot so it begins processing new messages again.
-
neuron_resume_campaignExecuteResume a previously paused campaign to restart message delivery.
-
neuron_set_presenceExecuteSet typing indicator or online/offline presence on a WhatsApp chat. Only supported on Baileys channels.
-
neuron_start_channel_sessionExecuteStart a Baileys (direct WhatsApp) session for the channel. Generates a QR code for device pairing. Only applicable to Baileys-type channels.
-
neuron_stop_channel_sessionExecuteStop the active Baileys session for the channel and disconnect from WhatsApp. The channel can be restarted later.
-
neuron_sync_knowledgeExecuteTrigger a synchronization operation to refresh embeddings, reindex content, or update the knowledge base state.
-
neuron_takeover_conversationExecuteTransfer control of a conversation from the bot to a human agent. The bot will stop auto-responding until the conversation is released.
-
neuron_test_toolExecuteExecute a dry-run test of a custom API tool with sample arguments to verify the endpoint responds correctly.
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.