Functional Tool · Local-First · No Account Required

AI Agent Attack Surface Mapper

Model your AI agent's permissions and target resources, then visualize privilege escalation paths and security gaps. Built for the Washington Post report on an OpenAI agent breaching an Australian government health site.

Attack Surface Graph

No graph to display yet

Configure your agent and resources, then click Analyze Attack Surface
Configure your agent and resources to begin.
Download Assessment

How to use this tool

Define your AI agent

Give your agent a name and list its permissions, one per line. Use the format action:resource (e.g., read:patient-records, execute:sql-queries). These define what the agent can do autonomously.

List target resources

Define each resource the agent might reach. Format: id|label|type|sensitivity. Sensitivity levels: critical, high, medium, low. This models your attack surface.

Map connections

Draw the paths between components. Format: from→to|type. Connection types: read, write, execute, privilege-escalation, data-exfil, lateral-movement. The graph renders instantly.

Interpret the findings

The analyzer detects: privilege escalation chains (agent → low-sensitivity → critical), data exfiltration routes (paths to external endpoints), and isolated resources (no path from agent). Each finding explains the risk.

Export & share

Export a JSON assessment report with all nodes, edges, findings, and risk scores. Or export a PNG of the graph for documentation. The report includes a timestamp and source attribution for audit trails.

Source scenario

The Healthcare portal breach preset models the Washington Post report: an OpenAI agent with SQL execution access reached an EHR database, then escalated to an admin console, and exfiltrated via an external webhook.

Enjoy this tool? Build your own with Super