AI agents invoke kinbox_resume_campaign to trigger actions in Kinbox. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Resuming a paused campaign triggers external operations — sending messages to potentially large numbers of contacts via WhatsApp/Instagram/multi-channel. This is an operational trigger with significant blast radius (mass messaging), making it Execute at high severity. It is not Write (doesn't just modify data) nor Destructive (doesn't delete anything), but it initiates an ongoing external process.
From the tool's definition Retoma uma campanha pausada (Resumes a paused campaign)
Attacks that exploit this kind of access
Retoma uma campanha pausada. It is categorised as a Execute tool in the Kinbox MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kinbox MCP server in PolicyLayer and add a rule for kinbox_resume_campaign: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Kinbox. Nothing to install.
kinbox_resume_campaign is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the kinbox_resume_campaign rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for kinbox_resume_campaign. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
kinbox_resume_campaign is provided by the Kinbox MCP server (vergamini65-boop/kinbox-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →