Run a deterministic authenticated web scan (no LLM required). Logs in, crawls same-host pages, probes each parameterized endpoint with SQLi/XSS/command-injection payloads. Returns structured findings suitable for the findings database. Recommended (secure): pass auth_profile = name of a profile c...
AI agents invoke authenticated_scan to trigger actions in Pentest Ai. 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.
This tool actively executes security probes against web applications — logging in, crawling pages, and firing attack payloads (SQLi, XSS, command injection). This constitutes active exploitation/testing against external systems, making it Execute category.
From the tool's definition Run a deterministic authenticated web scan... Logs in, crawls same-host pages, probes each parameterized endpoint with SQLi/XSS/command-injection payloads
Documented attack patterns abuse exactly the kind of access authenticated_scan gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pentest Ai, and nothing reaches the server without passing your rules. This is the rule we recommend for authenticated_scan:
{
"version": "1",
"default": "deny",
"tools": {
"authenticated_scan": {
"limits": [
{
"counter": "authenticated_scan_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}authenticated_scan 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 a deterministic authenticated web scan (no LLM required). Logs in, crawls same-host pages, probes each parameterized endpoint with SQLi/XSS/command-injection payloads. Returns structured findings suitable for the findings database. Recommended (secure): pass auth_profile = name of a profile created via pentest-ai auth profile add. Credentials are resolved server-side and never enter the MCP request payload (so they never reach the LLM). Deprecated (insecure, removed in 0.11): login_url + username + password for form login, or bearer_token for a static API token. These pass the credential value through the MCP/LLM context. When engagement_id is set, findings are persisted to the DB. It is categorised as a Execute tool in the Pentest Ai MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Pentest Ai MCP server in PolicyLayer and add a rule for authenticated_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 Pentest Ai. Nothing to install.
authenticated_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 authenticated_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 authenticated_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.
authenticated_scan is provided by the Pentest Ai MCP server (0xsteph/pentest-ai). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 51 Pentest Ai tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
51 Pentest Ai tools catalogued and risk-classified — across an index of 42,500+ MCP servers.