Skip to main content
Guardrails inspect calls that pass through Passport. They can check the request before an app receives it and the result before an AI client sees it. Built-in secret detection protects every plan. Runtime Security and custom rules require Enterprise.

​
Start with Runtime Security

Open Guardrails. In the Runtime Security card, choose a mode and what to inspect:
  • tool names and descriptions before a tool is exposed;
  • call arguments before execution;
  • text results before they reach the AI client.
Start with Observe. It records findings without changing calls, so you can see what would happen before turning on enforcement. The results card shows observed, blocked, and critical counts, plus recent findings.
Runtime Security is explainable and intentionally conservative. It does not claim to detect every malicious instruction. Images, audio, and binary content are size-limited but are not understood semantically.

​
What it looks for

Runtime Security recognizes categories such as instruction override, hidden instruction characters, secret-exfiltration instructions, access-control bypass, destructive commands, and resource abuse. Passport checks block rules against the original content before applying redactions. That prevents one rule from hiding a match from another. Security findings store only bounded metadata: app, tool, phase, category, severity, action, reason, and a one-way fingerprint. Passport does not store the matching request or result in the finding.

​
Built-in secret detection

Every workspace has a rule that catches common credentials before they cross the wire in either direction, including:
  • AWS access keys
  • GitHub tokens
  • Slack tokens
  • OpenAI keys
  • Stripe keys
  • PEM private keys
  • Passport’s own session, access, refresh, and agent-key tokens
  • password assignments
The rule scans the full text payload up to 5 MB, including secrets deep inside a file read or database result.

​
Rule actions

Block

Stop the call and raise an alert.

Redact

Replace the match with a marker and allow the cleaned call.

Alert

Allow the call and record the match.

​
Add a custom rule

In the Rules card, choose Add from library or New rule. A rule can inspect arguments, results, or both, and can apply everywhere or only to selected apps. Custom rules accept a regular expression or a plain phrase. Passport rejects patterns that are too long or unsafe to run on every call, and limits how much text a custom pattern scans.

​
Alerts and stored records

A match raises an alert. Runtime Security findings can also be exported as metadata-only security events or streamed to a security system. Guardrails protect Activity itself: content that a guardrail flags is scrubbed before the record is stored, so a blocked credential cannot reappear in Activity or an export. The exception is a custom alert-only rule, which is explicitly meant to surface the matched content for review. See SIEM and OTLP export.