Vulnerability · Published Jan 29, 2026 · Assigned by GitHub_M

CVE-2026-24780AutoGPT is Vulnerable to RCE via Disabled Block Execution

High 8.6

In plain English

A high-severity incorrect authorization in AutoGPT from Significant-Gravitas. Proof-of-concept exploit code is public. The chance it is exploited in the next 30 days is estimated at 1.3% (higher than 70% of all known vulnerabilities).

Severity (CVSS 4.0)8.6High
Exploit odds (30 days)1.3%top 30.3% of all CVEs
Exploited in the wildNo reportsCISA SSVC: poc
Attack toolingNoneno public tooling known

Official description

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that automate complex workflows. Prior to autogpt-platform-beta-v0.6.44, AutoGPT Platform's block execution endpoints (both main web API and external API) allow executing blocks by UUID without checking the `disabled` flag. Any authenticated user can execute the disabled `BlockInstallationBlock`, which writes arbitrary Python code to the server filesystem and executes it via `__import__()`, achieving Remote Code Execution. In default self-hosted deployments where Supabase signup is enabled, an attacker can self-register; if signup is disabled (e.g., hosted), the attacker needs an existing account. autogpt-platform-beta-v0.6.44 contains a fix.

Affected packages & fixed versions

EcosystemPackageFixed inAdvisory
PyPIagptno fix listedGHSA-r277-3xc5-c79v
PyPIagptno fix listedPYSEC-2026-1078

Affected products (as reported)

VendorProductVersions
Significant-Gravitas AutoGPT >= 0.1.0, < 0.6.44

Weakness: CWE-863, CWE-94, CWE-276 · 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:P

References