PT-2024-18387 · Significant Gravitas · Autogpt

Published 2024-06-06 · Updated 2025-08-05 · CVE-2024-1879

Positive Technologies (AI Summary)

CVSS v3.1

8.8

High

Base vector

AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H

Name of the Vulnerable Software and Affected Versions significant-gravitas/autogpt version v0.5.0

Description A Cross-Site Request Forgery (CSRF) issue allows attackers to execute arbitrary commands on the AutoGPT server. The vulnerability stems from the lack of protections on the API endpoint receiving instructions, enabling an attacker to direct a user running AutoGPT in their local network to a malicious website. This site can then send crafted requests to the AutoGPT server, leading to command execution. The issue is exacerbated by CORS being enabled for arbitrary origins by default, allowing the attacker to read the response of all cross-site queries.

Recommendations Update to version 5.1 to patch this vulnerability. As a temporary workaround, consider restricting access to the API endpoint receiving instructions until the update is applied. Additionally, disabling CORS for arbitrary origins can help minimize the risk of exploitation.

Exploit

Fix

CSRF

Weakness Enumeration

CWE-352

Related Identifiers

CVE-2024-1879

Affected Products

Autogpt

References · 9

• 🔥 https://huntr.com/bounties/125c2d0c-0481-4e5c-ae90-fec263acdf32 · Exploit
• https://github.com/significant-gravitas/autogpt/commit/26324f29849967fa72c207da929af612f1740669 · Patch
• https://osv.dev/vulnerability/CVE-2024-1879 · Vendor Advisory
• https://nvd.nist.gov/vuln/detail/CVE-2024-1879 · Security Note
• https://twitter.com/CveFindCom/status/1798777282624147519 · Twitter Post
• https://t.me/cvenotify/82298 · Telegram Post
• https://t.me/cveNotify/130934 · Telegram Post
• https://t.me/cvenotify/95790 · Telegram Post
• https://twitter.com/CVEnew/status/1798781399140626910 · Twitter Post