Exploit discussion active in current signal (1 latest mentions)
Recommended action window: High priority (within 72h)
NVD description
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.
Priority
LOW
Exploitation
NONE
PoC
YES
Patch
AVAILABLE
Momentum
STABLE
If you run products in this scope, you should treat this CVE as relevant to your environment.
| Date | Total | Labels |
|---|
| 2026-02-12 | 1 | General1 |
| 2026-02-13 | 1 | Patch1 |
| 2026-02-15 | 1 | Disclosure1 |
| 2026-03-07 | 1 | Disclosure1 |
| 2026-03-08 | 1 | Patch1 |
| 2026-03-09 | 1 | Disclosure1 |
| 2026-03-10 | 1 | Disclosure1 |
| 2026-03-11 | 1 | Disclousure1 |
| 2026-03-12 | 1 | Disclosure1 |
| 2026-03-13 | 1 | Patch1 |
| 2026-03-14 | 1 | Disclosure1 |
CVE-2026-26020 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 a… https://www.cve.org/CVERecord?id=CVE-2026-26020
Post summary
The post references CVE‑2026‑26020 but offers no additional detail on exploitation, patching, or technical specifics.
New vulnerability disclosed: CVE-2026-26020 with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Worth reviewing if this affects your stack. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
A new high‑severity vulnerability, CVE-2026‑26020 with a CVSS of 8.8, has been announced, accompanied by a link to further details, but no exploit code, patch, or active‑exploitation information is provided.
CVE-2026-26020 has been published with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Add it to your patching queue if applicable. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
CVE-2026-26020 has been disclosed with a CVSS of 8.8; the brief notes advise adding it to the patch queue.
Security advisory: CVE-2026-26020 with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Check if you need to take action. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
The text announces an advisory for CVE‑2026‑26020 with a high CVSS score, but it lacks PoC details, exploit code, active exploitation evidence, or patch information, indicating a straightforward disclosure.
Security advisory: CVE-2026-26020 with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Check if you need to take action. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
A security advisory highlights CVE-2026-26020 with a CVSS score of 8.8 and directs readers to an exploit radar for further details, but provides no PoC, patch, or evidence of active exploitation.
New vulnerability disclosed: CVE-2026-26020 with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Worth reviewing if this affects your stack. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
The post announces a newly disclosed CVE-2026-26020 with a CVSS of 8.8 and links to threatops for more details, but offers no PoC, exploit, or patch information.
Security advisory: CVE-2026-26020 with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Check if you need to take action. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
An advisory notes CVE‑2026‑26020 has a CVSS score of 8.8, directs readers to an external link for details, and does not provide exploit code, patch information, or evidence of active exploitation.
CVE-2026-26020 has been published with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Add it to your patching queue if applicable. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
The post notes that CVE-2026-26020, with a CVSS score of 8.8, has been published and advises adding it to patch queues.
CVE-2026-26020 has been published with a CVSS score of 8.8. AutoGPT is a platform that allows users to create,.... Add it to your patching queue if applicable. Details: https://threatops.tech/exploit-radar #CVE #InfoSec #VulnMgmt
Post summary
CVE-2026-26020 is a newly published vulnerability with a high CVSS score of 8.8; a link to additional exploit information is provided and users are advised to add it to their patching queue.
🚨 CVE-2026-26020: AutoGPT Affected by Remote Code ... Devastating auth bypass in AutoGPT exposes critical validation gap; embed disabled BlockInstallationBlock in graph to a... https://zerodaysignal.com/vulnerability/CVE-2026-26020 #netsec #vulnerability #CVE #sysadmin #zeroday
Post summary
The tweet announces the discovery of CVE‑2026‑26020 in AutoGPT, describing an authentication bypass that exposes a critical validation gap.
🚨 CRITICAL: AutoGPT (<0.6.48) allows authenticated users RCE via improper authorization. Upgrade now to protect your AI workflows! 🔒 https://radar.offseq.com/threat/cve-2026-26020-cwe-285-improper-authorization-in-s-31ca744c #OffSeq #AutoGPT #Vulnerability #AIsecurity https://t.co/XcRdfcZgq8
Post summary
The tweet highlights a critical RCE vulnerability in AutoGPT (v < 0.6.48) and urges users to upgrade to mitigate the issue.
1 of 1 entries
| Part | Vendor | Product | Version | Target SW | Target HW |
|---|---|---|---|---|---|
| App | agpt | autogpt_platform | - | - | - |