Your AI Agent Passed the Approval Check. Did the Side Effect?

说明与用途

Agent Action Guard 通过静态分析和运行时证据检测 OpenAI 代理的批准绕过，确保真实后果受到保护。

问题

AI agents may bypass approval boundaries via alternate execution paths, leading to unintended real-world consequences.

结果

The combined static and runtime approach successfully identified bypass paths and confirmed boundary enforcement, enabling developers to validate safety boundaries in CI pipelines.

工作流

• 1. Define approval boundary in agent workflow.
• 2. Run static scanner to detect possible counterexample paths.
• 3. Attach Runtime Witness hooks to OpenAI Agents SDK to record tool lifecycle events.
• 4. Execute agent with hooks in guarded mode to observe boundary usage.
• 5. Analyze runtime witness output for boundary verdict.
• 6. If OBSERVED_BYPASS or UNRESOLVED_TRACE, investigate and adjust agent or approval logic.

证据

The static scanner in the project looks for that second path.

来源

The runtime layer asks: «What path was actually observed when the protected consequence occurred?»

来源

If the execution evidence is incomplete, the system does not infer safety and does not infer a bypass.

来源