CVE-2025-22603: AutoGPT SSRF vulnerability
First published: Mon Mar 10 2025(Updated: )
AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Versions prior to autogpt-platform-beta-v0.4.2 contains a server-side request forgery (SSRF) vulnerability inside component (or block) `Send Web Request`. The root cause is that IPV6 address is not restricted or filtered, which allows attackers to perform a server side request forgery to visit an IPV6 service. autogpt-platform-beta-v0.4.2 fixes the issue.
Credit: security-advisories@github.com
| Affected Software | Affected Version | How to fix |
|---|---|---|
| AutoGPT | <autogpt-platform-beta-v0.4.2 |
Never miss a vulnerability like this again
Sign up to SecAlerts for real-time vulnerability data matched to your software, aggregated from hundreds of sources.
Reference Links
- https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4c8v-hwxc-2356
- https://github.com/Significant-Gravitas/AutoGPT/commit/26214e1b2c6777e0fae866642b23420adaadd6c4
- https://boatneck-faucet-cba.notion.site/SSRF-of-AutoGPT-153b650a4d88804d923ad65a015a7d61
- https://github.com/Significant-Gravitas/AutoGPT/blob/2121ffd06b26a438706bf642372cc46d81c94ddc/autogpt_platform/backend/backend/util/request.py#L11
Frequently Asked Questions
What is the severity of CVE-2025-22603?
CVE-2025-22603 is considered a high severity vulnerability due to its potential for server-side request forgery exploitation.
How do I fix CVE-2025-22603?
To fix CVE-2025-22603, upgrade to AutoGPT version autogpt-platform-beta-v0.4.2 or later.
What type of vulnerability is CVE-2025-22603?
CVE-2025-22603 is classified as a server-side request forgery (SSRF) vulnerability.
Which versions of AutoGPT are affected by CVE-2025-22603?
All versions of AutoGPT prior to autogpt-platform-beta-v0.4.2 are affected by CVE-2025-22603.
What impact does CVE-2025-22603 have on users?
CVE-2025-22603 can allow attackers to manipulate server requests, potentially leading to data exposure or system compromise.
- collector/mitre-cve
- source/MITRE
- agent/title
- agent/references
- agent/weakness
- agent/first-publish-date
- agent/type
- agent/description
- agent/guess-ai
- agent/software-canonical-lookup
- agent/software-canonical-lookup-request
- agent/softwarecombine
- collector/nvd-api
- source/NVD
- agent/severity
- agent/last-modified-date
- agent/author
- agent/source
- agent/tags
- agent/event
- vendor/autogpt
- canonical/autogpt