What this tool expects
Paste complete agent configuration or policy bundle. JSON, YAML, policy text, prompt fragments or logs can be analyzed together.
Agent Security · Free · No registration
AI Agent Security Scanner
Analyze AI agent permissions, tools, prompts, credentials, workflows, browser access, network access, delegation and approval controls.
Input: Paste complete agent configuration or policy bundle
🔒 Submitted text is analyzed on this server for this request and is not intentionally stored by the application.
What the result means
The result is specific to the full checks enabled for this tool. Evidence is shown next to each supported finding so you can verify what triggered it.
Privacy-first analysis
The application does not call third-party AI APIs and never executes uploaded content. Do not intentionally submit live credentials. Rotate a real secret if one is exposed.
Recommended workflow
Use the realistic sample to understand the expected input, scan your own sanitized evidence, review high-impact findings first, then validate the corresponding runtime control.