I built a scanner for AI-agent approval bypass paths

Description and use

The scanner detects approval bypass paths that let AI agents deploy to production without proper approval.

Problem

AI agents may bypass expected approval boundaries to reach production, creating security gaps.

Outcome

The scanner successfully identified counterexamples where AI agents could reach production deployment without passing through the approval boundary, providing actionable evidence for remediation.

Workflow

• 1. Install the scanner via pip. 2. Run the scanner against a target repository, specifying the consequence (e.g., production_deploy) and the boundary (e.g., approval).
• 3. The scanner builds a modeled consequence path across Python and GitHub Actions.
• 4. It searches for alternative modeled routes to the same consequence that do not cross the expected approval boundary.
• 5. If such a path is found, it outputs COUNTEREXAMPLE_FOUND, the path, and source‑code evidence; otherwise it returns UNKNOWN or COVERED_WITHIN_MODEL.

Evidence

I built an early open-source scanner to look for this specific class of problem.

Source

It deliberately does not claim full repository completeness.

Source