LangGraph agent runs tools with no human checkpoint
MediumAV-FW-018Human oversightFramework packNew in 2.0
What it finds
A LangGraph agent has tools that change things (send, delete, pay, deploy…) and no interrupt for human review.
Why it matters
LangGraph supports pausing before a tool runs so a person can approve it. Without it, write actions happen on the model's decision alone.
What an attacker could do: Consequential actions run without a person seeing them first.
How to fix it
Add interrupt_before=["tools"] (or interrupt() inside sensitive tools) and resume only after approval.
Pro shows the corrected code for your exact file, step by step, and re-scans to confirm the fix. See plans
Check details
- Finding code
- LANGGRAPH_TOOLS_NO_INTERRUPT
- How it detects
- Looks for a risky pattern, and stays quiet when a matching safeguard is present.
- Confidence
- Likely: strong signal, but review it in context.
- Scans
- Agent source using the named framework (LangChain, CrewAI, AutoGen, OpenAI Agents SDK, Claude Agent SDK, computer-use tools)
- OWASP LLM Top 10
- LLM08 - Excessive Agency
- NIST AI RMF
- MG-2.2
- SOC 2
- CC6.1
Check your agent for this
Paste your agent code or MCP config. The free scan runs all 124 checks in about 10 seconds — no account needed.
Related checks
- Agent can move money with no amount limitAV-HUMAN-003 · Critical
- Missing human-in-the-loop gatesAV-HUMAN-001 · High
- Built-in safety controls turned offAV-HUMAN-002 · High
- Destructive tool with no confirmationAV-HUMAN-004 · High
- AI editor set to run every tool without askingAV-FW-013 · High
- OpenAI Agents SDK agent with tools but no guardrailsAV-FW-006 · Medium