AI agents invoke generate_poc 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.
A proof-of-concept in a penetration testing context means crafting working exploit code or attack payloads to demonstrate exploitability of a vulnerability. This constitutes an Execute-level action with high severity since it produces functional attack artifacts within an autonomous pentest platform, and misuse could result in active exploitation of systems.
From the tool's definition 'Generate proof of concept for a finding' — generating a PoC involves constructing and potentially executing exploit code or attack demonstrations against a target system
Documented attack patterns abuse exactly the kind of access generate_poc 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 generate_poc:
{
"version": "1",
"default": "deny",
"tools": {
"generate_poc": {
"limits": [
{
"counter": "generate_poc_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}generate_poc 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.
Generate proof of concept for a finding. 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 generate_poc: 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.
generate_poc 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 generate_poc 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 generate_poc. 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.
generate_poc 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.