Authenticated denial of service via unbounded media storage
Published Jun 18, 2026 · Updated Jun 18, 2026
Uncontrolled resource consumption in AutoGPT before 0.6.63 allows remote authenticated users to interrupt service by exhausting disk space. AddAudioToVideoBlock downloads attacker-selected video and audio without size limits, retains inputs until graph completion, and leaves the generated video in the working directory. A low-privileged account can combine unbounded StepThroughItemsBlock loops or a long completion delay with repeated media retrieval, filling storage until the platform becomes unavailable.
Summary
What happened
Uncontrolled resource consumption in AutoGPT before 0.6.63 allows remote authenticated users to interrupt service by exhausting disk space. AddAudioToVideoBlock downloads attacker-selected video and audio without size limits, retains inputs until graph completion, and leaves the generated video in the working directory. A low-privileged account can combine unbounded StepThroughItemsBlock loops or a long completion delay with repeated media retrieval, filling storage until the platform becomes unavailable.
The record
- CVE
- CVE-2025-32436
- Published
- Jun 18, 2026
- Updated
- Jun 18, 2026
- Vendor
- Significant Gravitas
- Product
- AutoGPT
- Classifications
- CWE-400, T1499.004
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jun 18, 2026CVE publishedPublication date reported by the CVE source.
- Jun 18, 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=< 0.6.63
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
- GHSA-g26x-xwc5-7p44 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