I built a scanner for AI-agent approval bypass paths

说明与用途

扫描器检测到绕过审批路径，允许 AI 代理在未获得适当批准的情况下将代码部署到生产环境。

问题

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

结果

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

工作流

• 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.

证据

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

来源

It deliberately does not claim full repository completeness.

来源