PT-2025-10613 · Unknown · Autogpt-Platform

Agentsec · Published 2025-03-10 · Updated 2026-01-28 · CVE-2025-22603

Positive Technologies (AI Summary)

CVSS v4.0

8.7

High

Base vector

AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N

Name of the Vulnerable Software and Affected Versions autogpt-platform versions prior to autogpt-platform-beta-v0.4.2

Description The issue is related to a server-side request forgery (SSRF) vulnerability inside the Send Web Request component. The root cause is that IPV6 addresses are not restricted or filtered, allowing attackers to perform a server-side request forgery to visit an IPV6 service.

Recommendations For versions prior to autogpt-platform-beta-v0.4.2, update to autogpt-platform-beta-v0.4.2 to fix the issue. As a temporary workaround, consider restricting access to the Send Web Request component to minimize the risk of exploitation.

Exploit

Fix

SSRF

Weakness Enumeration

CWE-918

Related Identifiers

CVE-2025-22603

GHSA-4C8V-HWXC-2356

Affected Products

Autogpt-Platform

References · 11

• 🔥 https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/22xxx/CVE-2025-22603.json · Exploit
• 🔥 https://boatneck-faucet-cba.notion.site/SSRF-of-AutoGPT-153b650a4d88804d923ad65a015a7d61 · Exploit
• https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4c8v-hwxc-2356 · Vendor Advisory
• https://github.com/Significant-Gravitas/AutoGPT/commit/26214e1b2c6777e0fae866642b23420adaadd6c4 · Patch
• https://osv.dev/vulnerability/CVE-2025-22603 · Vendor Advisory
• https://nvd.nist.gov/vuln/detail/CVE-2025-22603 · Security Note
• https://github.com/Significant-Gravitas/AutoGPT/blob/2121ffd06b26a438706bf642372cc46d81c94ddc/autogpt_platform/backend/backend/util/request.py#L11 · Note
• https://t.me/cvetracker/18837 · Telegram Post
• https://twitter.com/cybercronai/status/1899728398357770511 · Twitter Post
• https://twitter.com/CVEnew/status/1899169585024176362 · Twitter Post
• https://t.me/cveNotify/150163 · Telegram Post