CVE-2025-62615
📋 TL;DR
This CVE describes a Server-Side Request Forgery (SSRF) vulnerability in AutoGPT's RSSFeedBlock component. Attackers can exploit unfiltered URL inputs to make unauthorized requests to internal systems. Users running vulnerable AutoGPT versions with RSSFeedBlock functionality are affected.
💻 Affected Systems
- AutoGPT
📦 What is this software?
⚠️ Risk & Real-World Impact
Worst Case
Complete compromise of internal infrastructure, data exfiltration, or lateral movement to cloud metadata services and internal APIs.
Likely Case
Information disclosure from internal services, port scanning of internal networks, or limited data access.
If Mitigated
Minimal impact if network segmentation restricts outbound connections and internal services require authentication.
🎯 Exploit Status
SSRF vulnerabilities typically have low exploitation complexity when unfiltered URL inputs are available.
🛠️ Fix & Mitigation
✅ Official Fix
Patch Version: autogpt-platform-beta-v0.6.34
Vendor Advisory: https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-r55v-q5pc-j57f
Restart Required: Yes
Instructions:
1. Update AutoGPT to version autogpt-platform-beta-v0.6.34 or later. 2. Restart the AutoGPT service. 3. Verify the update was successful.
🔧 Temporary Workarounds
Disable RSSFeedBlock
allTemporarily disable RSSFeedBlock functionality until patching is possible
Modify configuration to remove or disable RSSFeedBlock components
Network Restriction
allImplement network controls to restrict outbound connections from AutoGPT instances
Configure firewall rules to limit AutoGPT's network access
🧯 If You Can't Patch
- Implement strict network segmentation to isolate AutoGPT instances from sensitive internal systems
- Deploy web application firewalls (WAF) with SSRF protection rules
🔍 How to Verify
Check if Vulnerable:
Check AutoGPT version and verify if RSSFeedBlock is enabled in vulnerable versionsCheck Version:
Check AutoGPT configuration or package manager for installed versionVerify Fix Applied:
Confirm version is autogpt-platform-beta-v0.6.34 or later and test RSSFeedBlock functionality📡 Detection & Monitoring
Log Indicators:
- Unusual outbound HTTP requests from AutoGPT to internal IP addresses
- Requests to metadata services (169.254.169.254, etc.)
Network Indicators:
- HTTP traffic from AutoGPT to unexpected internal destinations
- Port scanning patterns originating from AutoGPT instances
SIEM Query:
source="autogpt" AND (dest_ip=169.254.169.254 OR dest_ip IN [RFC1918 ranges])