# Help Passing urlscan.io JSON to OpenAI Node for Analysis **URL:** \ **Category:** Questions\ **Tags:** workflow-building\ **Created:** [August 18, 2025, 5:44pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184 "2025-08-18T17:44:15Z")\ **Posts on this page:** 5\ **Page:** 1
**Author:** ![oytawil](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/oytawil/32/111148_2.png) [@oytawil](https://community.n8n.io/u/oytawil)\ **Post date:** [August 18, 2025, 5:44pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184/1 "2025-08-18T17:44:15Z")
## Describe the problem/error/question I am using this free workflow which uses [urlscan.io](http://urlscan.io) to get a report then pass it to chatgpt to summarize it, but after the report is generated chatgpt is unable to acess it or read it for someresons, not sure if i need to provide the api key or the scan need to be public ## What is the error message (if any)? I couldn’t analyze the provided [urlscan.io](http://urlscan.io) result. Please paste the urlscan JSON (or key details such as domains, IPs, indicators, and screenshots) and I will classify it accurately ## Please share your workflow using this exact workflow [Scan URLs for Security Threats with urlscan.io and GPT-4o mini | n8n workflow template](https://n8n.io/workflows/7159-scan-urls-for-security-threats-with-urlscanio-and-gpt-4o-mini/) ```auto (Select the nodes on your canvas and use the keyboard shortcuts CMD+C/CTRL+C and CMD+V/CTRL+V to copy and paste the workflow.) ``` ---
**Author:** ![jabbson](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/jabbson/32/87328_2.png) [@jabbson](https://community.n8n.io/u/jabbson)\ **Post date:** [August 18, 2025, 6:19pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184/2 "2025-08-18T18:19:49Z")
The issue is that in the AI Agent node you are referencing the URL of the result, not the result itself. On the other hand I assume the output could be too large to send to the LLM for analysis. ---
**Author:** ![oytawil](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/oytawil/32/111148_2.png) [@oytawil](https://community.n8n.io/u/oytawil)\ **Post date:** [August 18, 2025, 10:26pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184/3 "2025-08-18T22:26:33Z")
so ai can’t use URLs? and how can I pass the result? can I pass it as a file? ---
**Author:** ![jabbson](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/jabbson/32/87328_2.png) [@jabbson](https://community.n8n.io/u/jabbson)\ **Post date:** [August 18, 2025, 11:14pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184/4 "2025-08-18T23:14:09Z")
This depends on what you mean by “use”. If can see and understand the concept of the URL. If can go and download the content of a URL, but which ever way you choose to do it, the result of the scan that I did against one of my sites was 35000 lines of JSON. I am not certain you really want to pass that amount of info to LLM, whether it is a json OR a file. 35k lines will end up being about 450000 input tokens. Depending on a model, this can be either impossible to send that much, or will cost some money. If you believe your site scan will end up being rather small and do want to try, here is how you can do it. I scanned “[https://example.com](https://example.com)” and it was relatively small: ---
**Author:** ![system](https://dub1.discourse-cdn.com/n8n/user_avatar/community.n8n.io/system/32/195824_2.png) [@system](https://community.n8n.io/u/system)\ **Post date:** [August 25, 2025, 11:14pm UTC](https://community.n8n.io/t/help-passing-urlscan-io-json-to-openai-node-for-analysis/171184/5 "2025-08-25T23:14:41Z")
Closed on August 25, 2025, 11:14pm UTC This topic was automatically closed 7 days after the last reply. New replies are no longer allowed.