CVE-2026-26020Network attack vector

Authenticated code execution via disabled block graphs

Published Feb 12, 2026 · Updated Feb 12, 2026

Improper authorization in AutoGPT before 0.6.48 allows remote authenticated users to execute code through crafted agent graphs. The _validate_graph_get_errors() function accepted disabled BlockInstallationBlock nodes, which write attacker-controlled Python to disk and import it. A normal account is sufficient to execute code as the backend process, exposing its files, database access, environment secrets, and reachable services.

CVSS severity9.4
Critical
EPSS probability0.50%
Next 30 days · Sep 16, 2026
Known exploitationUnconfirmed
Based on sourced intelligence
Hinoki checkNot available
Coverage for this vulnerability

See if you're affected

Explore vulnerability checks for your environment with Hinoki.

Book a demo

Summary

What happened

Improper authorization in AutoGPT before 0.6.48 allows remote authenticated users to execute code through crafted agent graphs. The _validate_graph_get_errors() function accepted disabled BlockInstallationBlock nodes, which write attacker-controlled Python to disk and import it. A normal account is sufficient to execute code as the backend process, exposing its files, database access, environment secrets, and reachable services.

The record

CVE
CVE-2026-26020
Published
Feb 12, 2026
Updated
Feb 12, 2026
Vendor
Significant Gravitas
Product
AutoGPT
Classifications
CWE-285, T1059.006
Attack vector
network
Privileges
authenticated

Timeline

How it unfolded

  1. Feb 12, 2026CVE publishedPublication date reported by the CVE source.
  2. Feb 12, 2026Record updatedLatest update available in the CVE record.

Exploitability

Present is not the same as exploitable

Compare your product and version with the public record. A matching version still requires validation against your environment.

Is a vulnerable build present?

Compare these published version ranges with your installed build and any vendor patches.

  1. Affected versionversion=< 0.6.48

What conditions does exploitation require?

Attack vectornetwork
Required privilegesauthenticated

What is affected?

Significant Gravitas · AutoGPTversion=< 0.6.48

Published CVSS scores

8.8NIST NVDCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
9.4GitHub, Inc.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

CVSS describes severity. EPSS estimates exploitation probability.

Attacks

What attackers are doing with it

Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.

Daily unique IPsNo honeypot observations are available for this CVE in the selected window.

No observations available

Sep 10, 2026Sep 16, 2026
Latest reporting daySep 16, 2026
Latest daily unique IPsUnavailable
Prior 30-day averageUnavailable
SourceShadowserver honeypots (KEV)
Vectornetwork
Privilegesauthenticated
Known exploitationUnconfirmed
Public exploitUnconfirmed

Weakness, pattern, technique

CWE-285Improper Authorization
T1059.006Python

Public exploit references

No public exploit references are available in this record.

Labels summarize the accepted research assessment. They do not indicate a test against your environment.

Technologies

Your stack

See the directory against your own environment.

Your stack

Check the software in your environment

Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.

Book a demo