---
title: "Web AI Agent Audit"
canonical: https://trickest.com/library/web-ai-agent-audit
description: "Probe embedded web chat agents for injection, prompt leak, jailbreak, and role confusion with WebAgentAudit."
---

# Web AI Agent Audit

## Overview

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](/use-cases/continuous-security-testing). You seed page URLs, probe live hosts with [httpx](/tools/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](/library/mcp-trust-boundary-suite) (MCP server config). This Collection unit is the public-page agent path: URL inventory in, WebAgentAudit evidence out.

## Pipeline

1. Seed · Page URLs supplies the target URL list for the run.
2. Prep · Normalize URL list cleans and dedupes that inventory.
3. Inventory · HTTP probe uses httpx to confirm live pages.
4. Scan · WebAgentAudit runs injection, prompt leak, jailbreak, and role-confusion probes. Set `mode=assess` for probes; `detect` inventories widgets.
5. Results · Correlate merges scan output into findings, inventory, and retest_delta outputs.

## Inputs

- **Page URL list.** Pages that embed a chat or agent. Demo seeds exist; replace with your inventory.
- **httpx.** Live-host probe ahead of the agent scan.
- **WebAgentAudit.** Private vault Arsenal tool. `mode=detect` inventories widgets; `mode=assess` runs probes.

## Outputs

- **findings.jsonl.** Agent probe hits with remediation hints.
- **inventory.jsonl.** URLs and agents observed.
- **retest_delta.jsonl.** Schedule-as-diff scaffold when pages or agent configs change.

## Integrations

- [httpx](/tools/httpx)
- [WebAgentAudit](/tools/webagentaudit) (BHUSA 2026 Arsenal)

## Sample output

Sample shape from the correlate pack (illustrative, not a live KPI).

```jsonl
{"kind":"finding","title":"Prompt leak or jailbreak pattern on embedded agent","severity":"high"}
{"kind":"inventory","note":"Live page URL observed ahead of WebAgentAudit"}
{"kind":"retest_delta","note":"Schedule re-runs when the agent or page changes"}
```

## FAQ

### Is this an offline model eval?

No. It probes web-embedded agents on the URLs you seed. Edit Seed, then set Scan `mode=assess` when you want probes.

### Do I need LLM API keys on the graph?

No. WebAgentAudit is the Arsenal probe path. Optional keys, if a mode asks for them, can live in vault or on the node.

### Why schedule this?

Correlate emits `retest_delta.jsonl` so scheduled re-runs can surface agent posture change after deploys.

## Related workflows

- [MCP Trust Boundary Suite](/library/mcp-trust-boundary-suite). Reach for this instead when the surface is MCP server config, not an embedded web agent.
- [Coding Agent Policy Gate](/library/coding-agent-policy-gate). Reach for this instead when the job is coding-agent action policy on the operator machine, not an embedded web agent.
- [XSS Scanner](/library/xss-scanner). Reach for this instead when the job is classic web reflection bugs, not agent prompt abuse.

---
_Markdown source of https://trickest.com/library/web-ai-agent-audit._