AI agents use kali_upload to create or update resources in Zebbern Kali MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Zebbern Kali MCP environment.
Upload operations create or modify files, fitting the Write category. Severity is high because in the context of a penetration testing toolkit, uploading arbitrary files could introduce malicious payloads, exploitation tools, or data that could be used for further attacks—though the isolated container environment provides some containment.
From the tool's definition Tool name 'kali_upload' and context as part of a Kali Linux penetration testing toolkit indicates file upload capability.
Documented attack patterns abuse exactly the kind of access kali_upload gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Zebbern Kali MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for kali_upload:
{
"version": "1",
"default": "deny",
"tools": {
"kali_upload": {
"limits": [
{
"counter": "kali_upload_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}kali_upload stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
kali_upload. It is categorised as a Write tool in the Zebbern Kali MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Zebbern Kali MCP server in PolicyLayer and add a rule for kali_upload: 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 Zebbern Kali MCP. Nothing to install.
kali_upload is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the kali_upload 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 kali_upload. 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.
kali_upload is provided by the Zebbern Kali MCP server (zebbern/zebbern-kali-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 128 Zebbern Kali MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
128 Zebbern Kali MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.