Logo
-

Byte Open Security

(ByteOS Network)

Log In

Sign Up

ByteOS

Security
Vulnerability Details
Registries
Custom Views
Weaknesses
Attack Patterns
Filters & Tools
Vulnerability Details :

CVE-2026-26020

Summary
Assigner-GitHub_M
Assigner Org ID-a0819718-46f1-4df5-94e2-005712e83aaa
Published At-12 Feb, 2026 | 20:52
Updated At-12 Feb, 2026 | 21:04
Rejected At-
Credits

AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.

Vendors
-
Not available
Products
-
Metrics (CVSS)
VersionBase scoreBase severityVector
Weaknesses
Attack Patterns
Solution/Workaround
References
HyperlinkResource Type
EPSS History
Score
Latest Score
-
N/A
No data available for selected date range
Percentile
Latest Percentile
-
N/A
No data available for selected date range
Stakeholder-Specific Vulnerability Categorization (SSVC)
▼Common Vulnerabilities and Exposures (CVE)
cve.org
Assigner:GitHub_M
Assigner Org ID:a0819718-46f1-4df5-94e2-005712e83aaa
Published At:12 Feb, 2026 | 20:52
Updated At:12 Feb, 2026 | 21:04
Rejected At:
▼CVE Numbering Authority (CNA)
AutoGPT Affected by Remote Code Execution via Dynamic Module Import in Block Loading (__import__)

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.

Affected Products
Vendor
Significant-Gravitas
Product
AutoGPT
Versions
Affected
  • < 0.6.48
Problem Types
TypeCWE IDDescription
CWECWE-285CWE-285: Improper Authorization
Type: CWE
CWE ID: CWE-285
Description: CWE-285: Improper Authorization
Metrics
VersionBase scoreBase severityVector
4.09.4CRITICAL
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Version: 4.0
Base score: 9.4
Base severity: CRITICAL
Vector:
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H
Metrics Other Info
Impacts
CAPEC IDDescription
Solutions

Configurations

Workarounds

Exploits

Credits

Timeline
EventDate
Replaced By

Rejected Reason

References
HyperlinkResource
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54
x_refsource_CONFIRM
https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32
x_refsource_MISC
https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48
x_refsource_MISC
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54
Resource:
x_refsource_CONFIRM
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32
Resource:
x_refsource_MISC
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48
Resource:
x_refsource_MISC
▼Authorized Data Publishers (ADP)
CISA ADP Vulnrichment
Affected Products
Metrics
VersionBase scoreBase severityVector
Metrics Other Info
Impacts
CAPEC IDDescription
Solutions

Configurations

Workarounds

Exploits

Credits

Timeline
EventDate
Replaced By

Rejected Reason

References
HyperlinkResource
Information is not available yet
▼National Vulnerability Database (NVD)
nvd.nist.gov
Source:security-advisories@github.com
Published At:12 Feb, 2026 | 21:16
Updated At:12 Feb, 2026 | 21:16

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to 0.6.48, an authenticated user could achieve Remote Code Execution (RCE) on the backend server by embedding a disabled block inside a graph. The BlockInstallationBlock — a development tool capable of writing and importing arbitrary Python code — was marked disabled=True, but graph validation did not enforce this flag. This allowed any authenticated user to bypass the restriction by including the block as a node in a graph, rather than calling the block's execution endpoint directly (which did enforce the flag). This vulnerability is fixed in 0.6.48.

CISA Catalog
Date AddedDue DateVulnerability NameRequired Action
N/A
Date Added: N/A
Due Date: N/A
Vulnerability Name: N/A
Required Action: N/A
Metrics
TypeVersionBase scoreBase severityVector
Secondary4.09.4CRITICAL
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
Type: Secondary
Version: 4.0
Base score: 9.4
Base severity: CRITICAL
Vector:
CVSS:4.0/AV:N/AC:L/AT:N/PR:L/UI:N/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X
CPE Matches

Weaknesses
CWE IDTypeSource
CWE-285Primarysecurity-advisories@github.com
CWE ID: CWE-285
Type: Primary
Source: security-advisories@github.com
Evaluator Description

Evaluator Impact

Evaluator Solution

Vendor Statements

References
HyperlinkSourceResource
https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32security-advisories@github.com
N/A
https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48security-advisories@github.com
N/A
https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54security-advisories@github.com
N/A
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32
Source: security-advisories@github.com
Resource: N/A
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48
Source: security-advisories@github.com
Resource: N/A
Hyperlink: https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54
Source: security-advisories@github.com
Resource: N/A

Change History

0
Information is not available yet

Similar CVEs

2Records found

CVE-2025-53944
Matching Score-6
Assigner-GitHub, Inc.
ShareView Details
Matching Score-6
Assigner-GitHub, Inc.
CVSS Score-7.7||HIGH
EPSS-0.06% / 18.93%
||
7 Day CHG~0.00%
Published-30 Jul, 2025 | 14:28
Updated-05 Aug, 2025 | 14:40
Rejected-Not Available
Known To Be Used In Ransomware Campaigns?-Not Available
KEV Added-Not Available
KEV Action Due Date-Not Available
AutoGPT Platform Exposes Graph Execution Results via Authorization Gap

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's get_graph_execution_results endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graph_id, it fails to verify ownership of the graph_exec_id parameter, allowing authenticated users to access any execution results by providing arbitrary execution IDs. The internal API implements proper validation for both parameters. This is fixed in v0.6.16.

Action-Not Available
Vendor-agptSignificant-Gravitas
Product-autogpt_platformAutoGPT
CWE ID-CWE-285
Improper Authorization
CWE ID-CWE-639
Authorization Bypass Through User-Controlled Key
CVE-2024-56320
Matching Score-4
Assigner-GitHub, Inc.
ShareView Details
Matching Score-4
Assigner-GitHub, Inc.
CVSS Score-9.4||CRITICAL
EPSS-0.73% / 72.20%
||
7 Day CHG+0.09%
Published-03 Jan, 2025 | 15:37
Updated-01 Aug, 2025 | 20:09
Rejected-Not Available
Known To Be Used In Ransomware Campaigns?-Not Available
KEV Added-Not Available
KEV Action Due Date-Not Available
GoCD vulnerable to admin privilege escalation by a malicious internal/existing authenticated user

GoCD is a continuous deliver server. GoCD versions prior to 24.5.0 are vulnerable to admin privilege escalation due to improper authorization of access to the admin "Configuration XML" UI feature, and its associated API. A malicious insider/existing authenticated GoCD user with an existing GoCD user account could abuse this vulnerability to access information intended only for GoCD admins, or to escalate their privileges to that of a GoCD admin in a persistent manner. it is not possible for this vulnerability to be abused prior to authentication/login. The issue is fixed in GoCD 24.5.0. GoCD users who are not able to immediate upgrade can mitigate this issue by using a reverse proxy, WAF or similar to externally block access paths with a `/go/rails/` prefix. Blocking this route causes no loss of functionality. If it is not possible to upgrade or block the above route, consider reducing the GoCD user base to more trusted set of users, including temporarily disabling use of plugins such as the guest-login-plugin, which allow limited anonymous access as a regular user account.

Action-Not Available
Vendor-thoughtworksgocd
Product-gocdgocd
CWE ID-CWE-285
Improper Authorization
Details not found