Python
CVE-2026-26020
HIGH
Attack ChainAIDerived
Hypothetical attack flow derived from CVE metadata – not a confirmed exploit chain
-
AccessAuthenticate to AutoGPT platform
-
DeliveryCreate graph with disabled BlockInstallationBlock
-
ExploitEmbed arbitrary Python code in block
-
ExecutionSubmit graph for execution
-
ImpactBackend server executes malicious code
Vulnerability Assessment
| Weakness |
CWE
OWASP Top 10:2025
A01:2025 - Broken Access Control
ASVS 5.0
V8 - Authorization Authorization verification
MITRE ATT&CK
1 technique across 1 tactic: Defense Evasion The technique list with ATT&CK links and the kill-chain view is part of the Basic plan and up. |
| Exploitation Conditions | Authenticated user account on AutoGPT versions prior to 0.6.48. Graph validation does not enforce disabled=True flag on BlockInstallationBlock nodes, allowing authenticated users to execute arbitrary Python code through graph submission. |
| Impact | CVSS 8.8 (HIGH). Attack vector: Network. Complexity: Low. Privileges required: Low. User interaction: None. Exploitation requires authentication. Exploitable via remote/network. |
| Exploit ScenarioDerived | A remote attacker (requires authentication) could exploit this vulnerability to create, deploy, and manage continuous artificial intelligence agents that automa. |
Get an e-mail when this CVE is exploited, patched or re-scored. Free account.
Alert meAnalysisAIv1 – Mar 12, 2026
Remote code execution in AutoGPT prior to version 0.6.48 allows authenticated users to execute arbitrary Python code on the backend server by embedding a disabled BlockInstallationBlock within a workflow graph, bypassing validation controls that only checked the disabled flag at direct execution endpoints. An attacker with valid credentials can exploit this to gain full control over the backend system and automate malicious workflows. The vulnerability has been patched in version 0.6.48 and all users should upgrade immediately.
Earlier versions of this analysis (1)
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. [CVSS 8.8 HIGH]
RemediationAI
A vendor patch is available — apply it immediately. Fixed in version 0.6.48.. Restrict network access to the affected service where possible.
Affects your stack
Find out whether the stacks and servers you run are on an affected version.
Checking this CVE against your own stacks and servers is part of the Basic plan and up.
Technical ContextAI · show details
Classified as CWE-285 (Improper Authorization). Affects Autogpt Platform. 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 authentica
Know when Python gets its next vulnerability
- Watch products and get an email when something new is published
- Check this CVE against your own stack and servers
- Exploit and PoC references, threat intelligence from 22 sources
No credit card · 7-day full trial
Severity by source
AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Primary rating from GitHub Advisory · only source for this CVE.
CVSS VectorGitHub Advisory
Lifecycle Timeline
2DescriptionGitHub Advisory
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.
Executive ViewAI
AutoGPT versions prior to 0.6.48 contain a critical vulnerability allowing authenticated users to execute arbitrary code on backend servers through manipulated workflow graphs. Organizations using AutoGPT for production automation workflows face immediate risk of system compromise, data theft, and operational disruption if users with platform access are compromised or malicious.
Apply vendor patch. If immediate patching is not possible: (1) Restrict AutoGPT platform access to minimum required personnel with mandatory MFA; (2) Implement network segmentation isolating AutoGPT backend from critical systems; (3) Deploy application-level monitoring to detect disabled blocks in graph deployments; (4) Disable workflow graph deployment features until patch is applied.
Threat Intelligence Overview
NVD
CVE.org
EPSS
GitHub
How this decision was reached
The engine reads each signal below and applies a fixed list of rules from top to bottom. The first rule that matches sets the recommended action – like a statement, every line is shown.
What every action level means
SSVC AssessmentENISA
Priority Score
Attack Technique
Remote Code Execution represents the critical moment when an attacker successfully runs arbitrary code on a target system without physical access.
Affected Products (CPE)GitHub Advisory
Wazuh SIEM platform versions 4.4.0 through 4.9.0 contain an unsafe deserialization vulnerability in the DistributedAPI t
BentoML version 1.4.2 and earlier contains an unauthenticated remote code execution vulnerability through insecure deser
pgAdmin 4 contains critical remote code execution vulnerabilities in the Query Tool download and Cloud Deployment endpoi
The renderLocalView function in render/views.py in graphite-web in Graphite 0.9.5 through 0.9.10 uses the pickle Python
BentoML is a Python library for building online serving systems optimized for AI apps and model inference. Rated critica
OpenSSL before 0.9.8za, 1.0.0 before 1.0.0m, and 1.0.1 before 1.0.1h does not properly restrict processing of ChangeCiph
pyLoad download manager version prior to 0.5.0b3.dev77 exposes the Flask SECRET_KEY through an unauthenticated endpoint.
Langflow (a visual LLM pipeline builder) contains a critical unauthenticated code execution vulnerability (CVE-2026-3301
In Mercurial before 4.1.3, "hg serve --stdio" allows remote authenticated users to launch the Python debugger, and conse
Unauthenticated remote code execution affects Kestra OSS (the open-source event-driven orchestration platform) prior to
Unauthenticated remote code execution in Marimo ≤0.20.4 allows attackers to execute arbitrary system commands via the `/
pyLoad is the free and open-source Download Manager written in pure Python. Rated medium severity (CVSS 5.3), this vulne
Exploit-DB