AI Agent Shields
☕ Support
Agent Security · Free · No registration

Agent Tool Capability Analyzer

Inspect declared tools and capabilities for high-impact actions and privilege concerns.

Input: Paste tool names and capability declarations
🔒 Submitted text is analyzed on this server for this request and is not intentionally stored by the application.
TOOLS INPUT

Paste tool names and capability declarations

List tools, actions and schemas that the agent can invoke.

Max 512 KiB
Files are read as text only and never executed.

What this tool expects

Paste tool names and capability declarations. List tools, actions and schemas that the agent can invoke.

What the result means

The result is specific to the tools 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.