AI agents invoke sn1per_scan to trigger actions in Kali. 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.
Sn1per is a comprehensive offensive security framework that executes active network scanning, vulnerability scanning, and exploitation workflows. It can trigger intrusive operations against external systems including port scanning, service enumeration, and automated exploitation. Running it against unauthorized targets is illegal, and misuse by an AI agent could cause significant harm to third-party systems.
From the tool's definition 'Execute Sn1per penetration testing framework' — Sn1per is an automated attack surface management and penetration testing framework that runs active reconnaissance, scanning, and exploitation modules against targets.
Attacks that exploit this kind of access
Execute Sn1per penetration testing framework. It is categorised as a Execute tool in the Kali MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali MCP server in PolicyLayer and add a rule for sn1per_scan: 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 Kali. Nothing to install.
sn1per_scan 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 sn1per_scan 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 sn1per_scan. 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.
sn1per_scan is provided by the Kali MCP server (pentestt00ls/kali-mcp-server). 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 →