Scanners
Find and probe the AI agents on your own web pages
webagentaudit is a tool from the Atom41 research team for security auditing of web-based AI agents through browser automation, auditing deployed chat and agent interfaces at scale through their real web surfaces rather than model or runtime APIs.
installgit clone https://github.com/atom41research/webagentaudit.gitpip install -e .
Python · AGPL-3.0 license
overview
What webagentaudit does
webagentaudit tests the AI agents that companies embed in their own web pages: the support chat, the shopping assistant, the onboarding bot. Those agents have no API you can point a scanner at. They exist only behind a widget, so the audit drives a real browser, finds the chat surface, and interacts with it the way a visitor would.
Mode selects how far it goes. detect looks for the chat surface and reports where it is. assess runs the algorithmic probes against a surface it has found. fixture replays a demo for shape checks. Because the probes are algorithmic rather than model driven, no provider API token is required, which keeps the node runnable on a schedule without a per-run cost.
Targets arrive as a single --url or a file on the url-file port, and the Web AI Agent Audit workflow probes hosts with httpx first so only live pages reach the browser stage. Output is findings.jsonl plus screenshots and reports, so an assessment leaves evidence a retest can be diffed against.
use cases
Where webagentaudit fits
Find which pages actually expose an agent
Run detect mode across a URL list to inventory the chat surfaces on your estate, including the ones a team shipped without telling anyone.
Probe a chat surface for agent-layer flaws
Switch to assess mode so the browser exercises the widget with algorithmic probes and records what the agent does in response.
Keep evidence for a retest
Screenshots and reports land beside findings.jsonl, so the next scheduled run can be compared against what the agent did last time.
Probe live hosts only
Chain httpx before the audit, as the Library workflow does, so browser automation runs against pages that resolve instead of the whole list.
reference
webagentaudit inputs and flags
| Name | Type | Flag | Description |
|---|---|---|---|
| url | STRING | --url | Single chat-page URL (optional if the urls file is set) |
| urls | FILE | --url-file | URL list file (one per line). Prefer seed to prep wiring, distribute per line. |
| mode | STRING | --mode | detect (find chat widget) | assess (run probes) | fixture (demo only) |
Showing key inputs. webagentaudit exposes 3 inputs in total.
example
Run webagentaudit
# find the chat surface on one page
webagentaudit --mode detect --url https://www.example.com/support
# probe a list of pages you are authorized to test
webagentaudit --mode assess --url-file urls.txt{
"tool": "webagentaudit",
"url": "https://www.example.com/support",
"mode": "assess",
"surface": "chat widget detected",
"probe": "system-prompt disclosure",
"result": "agent returned configuration text",
"severity": "medium"
}guidance
Choosing webagentaudit
Reach for webagentaudit when the agent is reachable only through a browser widget on a page you are authorized to test. Use mcparasite when the agent speaks MCP and the question is cross-channel propagation, and use httpx when you only need to know which pages are live.
mcparasite
Tests agents across MCP propagation channels. Same class of risk, reached through a protocol client rather than a browser.
httpx
Probes hosts and reports what responds. It finds the pages; it cannot interact with a chat widget rendered by JavaScript.
nuclei
Templates against the underlying web app. Runs beside an agent audit and covers the ordinary web surface, not the agent behaviour.
workflows
Workflows using webagentaudit
faq
webagentaudit questions
related
More Scanners tools
ac-scanner
BHUSA Arsenal TLS/SSH crypto inventory with post-quantum readiness signals and CBOM-shaped output.
airixss
Reflection triage for parameter URLs during recon.
bedrock-keys-security
Black Hat Arsenal hunting for phantom IAM users behind Bedrock keys, with offline key decode and org scan.
cmseek
CMS detection and version fingerprinting.
jaeles
Signature-driven web application scanner.
joomscan
OWASP Joomla vulnerability scanner for CMS flaws and misconfigurations.
Run webagentaudit yourself
A list of live page URLs feeds webagentaudit, which detects chat surfaces, probes them, and writes findings with screenshots.
Facts on this page come from the live Trickest tool library.