CVE-2024-48145
📋 TL;DR
A prompt injection vulnerability in Netangular Technologies ChatNet AI v1.0 allows attackers to bypass chat restrictions and exfiltrate all chat data, including previous conversations and future interactions. This affects all users of ChatNet AI v1.0 who use the chatbox functionality. The vulnerability enables unauthorized access to sensitive chat history between users and the AI assistant.
💻 Affected Systems
- Netangular Technologies ChatNet AI
⚠️ Manual Verification Required
This CVE does not have specific version information in our database, so automatic vulnerability detection cannot determine if your system is affected.
Why? The CVE database entry doesn't specify which versions are vulnerable (no version ranges provided by the vendor/NVD).
🔒 Custom verification scripts are available for registered users. Sign up free to download automated test scripts.
- Review the CVE details at NVD
- Check vendor security advisories for your specific version
- Test if the vulnerability is exploitable in your environment
- Consider updating to the latest version as a precaution
⚠️ Risk & Real-World Impact
Worst Case
Complete compromise of all chat data across all users, including sensitive personal information, business communications, and confidential data shared with the AI assistant, leading to data breaches and privacy violations.
Likely Case
Targeted exfiltration of specific users' chat histories containing personal information, credentials, or sensitive business data that could be used for identity theft, corporate espionage, or further attacks.
If Mitigated
Limited data exposure if chat data is properly segmented and access controls prevent cross-user data access, though prompt injection could still reveal some information.
🎯 Exploit Status
Exploitation requires sending a crafted message through the chat interface. The GitHub repository contains proof-of-concept details showing how to construct malicious prompts to exfiltrate data.
🛠️ Fix & Mitigation
✅ Official Fix
Patch Version: Not available
Vendor Advisory: Not available
Restart Required: No
Instructions:
No official patch available. Check Microsoft Store for updates to ChatNet AI. Consider uninstalling if no update is available.
🔧 Temporary Workarounds
Disable ChatNet AI
windowsUninstall or disable ChatNet AI v1.0 to prevent exploitation
Get-AppxPackage *ChatNet* | Remove-AppxPackage
Network Isolation
windowsBlock ChatNet AI from accessing the internet to prevent data exfiltration
New-NetFirewallRule -DisplayName "Block ChatNet AI" -Direction Outbound -Program "C:\Program Files\WindowsApps\[ChatNet_Package]\ChatNet.exe" -Action Block
🧯 If You Can't Patch
- Monitor network traffic from ChatNet AI for unusual outbound connections indicating data exfiltration
- Implement strict input validation and sanitization for all user inputs to the chat system
🔍 How to Verify
Check if Vulnerable:
Check if ChatNet AI v1.0 is installed via: Get-AppxPackage | Where-Object {$_.Name -like "*ChatNet*"} | Select-Object Name, VersionCheck Version:
Get-AppxPackage | Where-Object {$_.Name -like "*ChatNet*"} | Select-Object VersionVerify Fix Applied:
Verify ChatNet AI is uninstalled or updated to a version later than v1.0📡 Detection & Monitoring
Log Indicators:
- Unusual chat patterns with special characters or command-like structures
- Multiple rapid chat sessions from single users
- Chat logs containing system commands or data exfiltration attempts
Network Indicators:
- Unexpected outbound connections from ChatNet AI to external servers
- Large data transfers from ChatNet AI process
SIEM Query:
ProcessName="ChatNet.exe" AND (DestinationPort=443 OR DestinationPort=80) AND BytesSent>1000000