Service interruption via unbounded deep XML parsing
Published Feb 5, 2026 · Updated Feb 5, 2026
Resource exhaustion in AutoGPT before autogpt-platform-beta-v0.6.32 allows remote attackers to interrupt the server through a crafted RSS URL. ReadRSSFeedBlock passes the user-supplied URL directly to feedparser.parse without bounding download size, parsing time, or parser resource use, so deeply nested XML exhausts memory. Reachability requires the ability to make an agent run the RSS block against an attacker-controlled feed; the demonstrated consequence is server memory exhaustion and service interruption.
Summary
What happened
Resource exhaustion in AutoGPT before autogpt-platform-beta-v0.6.32 allows remote attackers to interrupt the server through a crafted RSS URL. ReadRSSFeedBlock passes the user-supplied URL directly to feedparser.parse without bounding download size, parsing time, or parser resource use, so deeply nested XML exhausts memory. Reachability requires the ability to make an agent run the RSS block against an attacker-controlled feed; the demonstrated consequence is server memory exhaustion and service interruption.
The record
- CVE
- CVE-2025-32393
- Published
- Feb 5, 2026
- Updated
- Feb 5, 2026
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-770, T1499.004
- Attack vector
- network
- Privileges
- Unavailable
Timeline
How it unfolded
- Feb 5, 2026CVE publishedPublication date reported by the CVE source.
- Feb 5, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< autogpt-platform-beta-v0.6.32
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Deep XML RSS feed proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo