PT-2025-12221 · Significant Gravitas · Autogpt

Published 2025-03-20 · Updated 2025-08-05 · CVE-2024-8156

Positive Technologies (AI Summary)

CVSS v3.1

9.8

Critical

Base vector

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

Name of the Vulnerable Software and Affected Versions significant-gravitas/autogpt versions up to and including the latest version

Description A command injection issue exists due to the insecure use of untrusted user input github.head.ref in the workflow-checker.yml workflow. This allows an attacker to inject arbitrary commands, potentially leading to reverse shell access or theft of sensitive tokens and keys. An attacker can exploit this by creating a branch name with a malicious payload and opening a pull request.

Recommendations For versions up to and including the latest version, update to a version that fixes this issue to prevent command injection attacks. As a temporary workaround, consider restricting the use of the github.head.ref input to minimize the risk of exploitation.

Exploit

Fix

Code Injection

Command Injection

Weakness Enumeration

CWE-94

CWE-77

Related Identifiers

CVE-2024-8156

Affected Products

Autogpt

References · 7

• 🔥 https://huntr.com/bounties/959efe87-f109-4cef-94d8-90ff2c7aef51 · Exploit
• https://github.com/significant-gravitas/autogpt/commit/1df7d527dd37dff8363dc162fb58d300f072e302 · Patch
• https://nvd.nist.gov/vuln/detail/CVE-2024-8156 · Security Note
• https://osv.dev/vulnerability/CVE-2024-8156 · Vendor Advisory
• https://twitter.com/CveFindCom/status/1902670953223725488 · Twitter Post
• https://t.me/cveNotify/130940 · Telegram Post
• https://twitter.com/CVEnew/status/1903019717977145731 · Twitter Post