Notion AI Vulnerability Enables Data Exfiltration Through Prompt Injection Attacks
By
takira
Pulled from the oven just right. Trustworthy, fact-dense, deeply satisfying.
Summary
Notion AI has a security vulnerability that allows data exfiltration through indirect prompt injection attacks. The vulnerability occurs because AI document edits are saved before user approval, enabling attackers to embed malicious prompts in documents like resumes or web pages that can extract sensitive data. The researchers responsibly disclosed the issue via HackerOne, but Notion closed the finding as 'Not Applicable'. The article demonstrates how this could be exploited to steal hiring tracker data through a poisoned resume.
Key quotes
· 5 pulledNotion AI is susceptible to data exfiltration via indirect prompt injection due to a vulnerability in which AI document edits are saved before user approval.
We responsibly disclosed this vulnerability to Notion via HackerOne. Unfortunately, they said 'we're closing this finding as `Not Applicable`'.
Stealing Hiring Tracker Data with a Poisoned Resume
The user uploads a resume (untrusted data) to their chat session.
Here, the untrusted data source is a resume PDF, but a prompt injection could be stored in a web page, connected data source, or a Notion page.
You might also wanna read
Prompt Injection Attacks: The Top Security Threat Hijacking AI Chatbots
Prompt injection attacks are a critical security vulnerability in AI systems where hidden instructions within user data (like emails or docu
buff.ly·7h ago
ChatGPT prompt injection vulnerability allows web pages to serve as phishing payloads
A security researcher discovered a prompt injection vulnerability in ChatGPT where the AI cannot distinguish between its own generated conte
buff.ly·2d ago
ChatGPT prompt injection vulnerability allows web pages to serve as phishing payloads
A security researcher discovered a prompt injection vulnerability in ChatGPT where the AI cannot distinguish between its own generated conte
theregister.com·1d ago
How hackers exploit AI chatbot personalities through prompt injection attacks
This article discusses how hackers are exploiting AI chatbot "personalities" through prompt injection and jailbreaking techniques. Initially
The Verge·7d ago
Google reports first evidence of hackers using AI to develop zero-day security exploit
Google has reported evidence of hackers using AI to develop a zero-day security vulnerability, marking the first time the company has observ
politico.com·6h ago