AI agents invoke scan_vulnerabilities to trigger actions in CHAI pentest tool. 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.
Vulnerability scanning actively probes external systems, sending network packets and triggering detection mechanisms. It is an active external operation whose effects depend on the target arguments. While not inherently destructive, it can disrupt services, trigger alarms, and cause unintended side effects on target systems.
From the tool's definition 'Run vulnerability scanning' on a pentest server described as 'autonomous penetration testing MCP server'; sibling tools include execute_command, generate_poc, run_autonomous_scan_tool
Documented attack patterns abuse exactly the kind of access scan_vulnerabilities gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and CHAI pentest tool, and nothing reaches the server without passing your rules. This is the rule we recommend for scan_vulnerabilities:
{
"version": "1",
"default": "deny",
"tools": {
"scan_vulnerabilities": {
"limits": [
{
"counter": "scan_vulnerabilities_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}scan_vulnerabilities stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Run vulnerability scanning. It is categorised as a Execute tool in the CHAI pentest tool MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the CHAI pentest tool MCP server in PolicyLayer and add a rule for scan_vulnerabilities: 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 CHAI pentest tool. Nothing to install.
scan_vulnerabilities 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 scan_vulnerabilities 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 scan_vulnerabilities. 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.
scan_vulnerabilities is provided by the CHAI pentest tool MCP server (nihar-sarkar/chai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from CHAI pentest tool, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
16 CHAI pentest tool tools catalogued and risk-classified — across an index of 43,000+ MCP servers.