loading
Probe embedded web chat agents for injection, prompt leak, jailbreak, and role confusion with WebAgentAudit.
Page URLs, one per line. Default includes a few public chat-widget demos.
Chat surfaces found and audit findings, plus report.json.
Live pages are probed, then any embedded chat widget is audited for injection, prompt leak, and role confusion.
Embedded web agents are a public-site attack surface. Injection, prompt leak, jailbreak, and role confusion need algorithmic probes on the pages you care about, not offline model eval theater.
This is a standing check for continuous security testing. You seed page URLs, probe live hosts with httpx, run BHUSA 2026 Arsenal WebAgentAudit for agent-oriented checks, and correlate findings you can schedule as a retest delta when the site or agent changes.
It sits next to MCP Trust Boundary Suite (MCP server config). This Collection unit is the public-page agent path: URL inventory in, WebAgentAudit evidence out.
mode=assess for probes; detect inventories widgets.mode=detect inventories widgets; mode=assess runs probes.Sample shape from the correlate pack (illustrative, not a live KPI).
| kind | title | severity | note |
|---|---|---|---|
| finding | Prompt leak or jailbreak pattern on embedded agent | high | null |
| inventory | null | null | Live page URL observed ahead of WebAgentAudit |
| retest_delta | null | null | Schedule re-runs when the agent or page changes |
No. It probes web-embedded agents on the URLs you seed. Edit Seed, then set Scan mode=assess when you want probes.
No. WebAgentAudit is the Arsenal probe path. Optional keys, if a mode asks for them, can live in vault or on the node.
Correlate emits retest_delta.jsonl so scheduled re-runs can surface agent posture change after deploys.
Get a personalized demo
A 30-minute walkthrough. We map the platform to your stack and answer pricing and deployment questions for your environment.