Perform security audit using Lynis. Scan types: system, full. Audits local system security.
AI agents invoke lynis_audit to trigger actions in Kali Linux Security Tools MCP Server. 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.
Lynis is a security auditing tool that actively probes the local system — examining configurations, running processes, installed packages, file permissions, and more. This constitutes execution of a scanning/auditing operation with real system-level access.
From the tool's definition Perform security audit using Lynis... Audits local system security
Attacks that exploit this kind of access
Perform security audit using Lynis. Scan types: system, full. Audits local system security. It is categorised as a Execute tool in the Kali Linux Security Tools MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Kali Linux Security Tools MCP Server MCP server in PolicyLayer and add a rule for lynis_audit: 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 Linux Security Tools MCP Server. Nothing to install.
lynis_audit 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 lynis_audit 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 lynis_audit. 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.
lynis_audit is provided by the Kali Linux Security Tools MCP Server MCP server (jesseeikeland/kali-linux-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 →