Raw 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:XSummary
CVE-2026-26020 is a critical-severity Improper Authorization (CWE-285) vulnerability in Agpt Autogpt Platform. Its CVSS base score is 9.4 (Critical).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 39th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Supply Chain and Deployment risk domain.
The strongest mitigations our analysis identified map to AC-24 (Access Control Decisions) and AC-25 (Reference Monitor) — see the control section below for these in your framework.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-26020 is a remote code execution (RCE) vulnerability (CWE-285: Improper Authorization) in the AutoGPT platform, which allows users to create, deploy, and manage continuous artificial intelligence agents for automating complex workflows. Versions prior to 0.6.48 are affected, specifically the backend server component. The flaw arises from the BlockInstallationBlock, a development tool capable of writing and importing arbitrary Python code, which was marked with disabled=True. However, graph validation failed to enforce this flag, permitting its misuse.
An authenticated user with low privileges can exploit this vulnerability remotely over the network with low complexity and no user interaction required. By embedding the disabled BlockInstallationBlock as a node within a graph—rather than invoking its execution endpoint directly, which did enforce the flag—the attacker bypasses restrictions and achieves RCE on the backend server. This grants high-impact confidentiality, integrity, and availability compromise, as reflected in the CVSS v3.1 base score of 8.8 (AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H).
The vulnerability is fixed in AutoGPT version 0.6.48. Mitigation involves updating to this release or later. Key resources include the patching commit at https://github.com/Significant-Gravitas/AutoGPT/commit/062fe1aa709217136b896c8b950e0f04435afb32, the release announcement at https://github.com/Significant-Gravitas/AutoGPT/releases/tag/autogpt-platform-beta-v0.6.48, and the GitHub security advisory at https://github.com/Significant-Gravitas/AutoGPT/security/advisories/GHSA-4crw-9p35-9x54.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-6688
Vulnerability Data
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Supply Chain and Deployment
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: artificial intelligence, autogpt
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Control response
—
—
- 6 hardening rules · 3 OS baselines
—
Mitigating Controls (NIST 800-53 r5) AI
Mandates that access-control decisions are made and applied to each request before access occurs.
Requires a tamperproof, always-invoked reference monitor that performs authorization checks.
Directly requires enforcement of approved authorizations for every access request, stopping improper or missing checks.
Limits granted privileges so that even a bypassed check affects fewer resources.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
PR.AA-05 mostly prevents CWE-285 via enforced policy, reviews, and least-privilege authorization decisions, yet CWE-285 remains only partially prevented because code-level check omissions or errors can still occur outside that single control.
Secure SDLC practices catch and eliminate most authorization defects before release, yet a single broad outcome cannot address every design, role, and runtime facet of CWE-285.
PR.AA-01 supplies managed identities and access-request workflows that can support downstream authorization decisions, yet does nothing to enforce or verify authorization checks inside a product, leaving CWE-285 fully unaddressed by this control alone.
Network segmentation/zero-trust limits external reachability (partial prevention of exploitation) but leaves application-level authorization logic untouched, so the CWE remains fully introducible and only one facet of its risk is addressed.
PR.PS-05 blocks unauthorized binaries/DNS while CWE-285 is an in-product authorization-check defect, so the control neither prevents the weakness nor removes any of its risk.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Granular, policy-driven assignment of permissions and dynamic enforcement of those permissions prevent the incorrect or missing authorization decisions that lead to improper authorization flaws.
By requiring documented authorization rules and periodic policy reviews, the control makes it less likely that authorization decisions will be omitted or implemented inconsistently across applications.
Mapping access rights to information classification and business requirements forces correct enforcement of authorization decisions, blocking the incorrect authorization weakness at the policy and implementation stage.
Independent reviewers evaluate whether authorization logic matches policy, thereby reducing the window in which incorrect or missing authorization checks remain in production.
By requiring managers to verify that authorization decisions match policy and to remediate deviations, the control limits the persistence of incorrect or missing authorization checks.
Requiring authorization processes and privilege assignments to be specified during project initiation prevents downstream components from receiving overly broad or incorrect rights that would allow unauthorized actions.
Hardening callouts derived
Configuration rules from DISA STIG baselines that bear on weaknesses of the type cited by this CVE. Each rule is shown with the relationship its mapping actually records, against the CWE it was authored against. Derived via CVE→CWE over `controls_xwalks` (authoritative rows only; rows rated `none` are excluded).
Oracle Linux 8 (2 rules)
- V-252656 The OL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-285
- V-248581 OL 8 must require users to provide a password for privilege escalation. prevents CWE-285
RHEL 7 (3 rules)
- V-204429 The Red Hat Enterprise Linux operating system must be configured so that users must provide a password for privilege escalation. prevents CWE-285
- V-204430 The Red Hat Enterprise Linux operating system must be configured so that users must re-authenticate for privilege escalation. prevents CWE-285
- V-251704 The Red Hat Enterprise Linux operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-285
RHEL 8 (1 rule)
- V-251712 The RHEL 8 operating system must not be configured to bypass password requirements for privilege escalation. prevents CWE-285