AI agents invoke openvas_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.
OpenVAS is an active vulnerability scanner that sends probes and exploits test cases against target hosts. This constitutes execution of external operations whose effects depend on the arguments (target host/network). It can cause disruption to target systems and constitutes unauthorized scanning if misused.
From the tool's definition Execute OpenVAS vulnerability scanner — actively scans target systems for vulnerabilities, triggering external network operations against potentially unauthorized targets
Attacks that exploit this kind of access
Execute OpenVAS vulnerability scanner. 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 openvas_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.
openvas_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 openvas_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 openvas_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.
openvas_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 →