How severe is CVE-2025-53944?

CVE-2025-53944 has a CVSS 3.x base score of 7.7, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability none.

Is CVE-2025-53944 being actively exploited?

It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (37th percentile), an estimate of the probability of exploitation in the next 30 days.

What products are affected by CVE-2025-53944?

CVE-2025-53944 affects Agpt Autogpt Platform. See the affected-products list for the exact vulnerable versions.

How do I fix CVE-2025-53944?

Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.

Does CVE-2025-53944 have an EU (EUVD) identifier?

Yes. CVE-2025-53944 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-23154.

When was CVE-2025-53944 published?

CVE-2025-53944 was published on 2025-07-30 and last updated on 2026-06-17.

CVE-2025-53944

CVE-2025-53944 is a high-severity vulnerability in Agpt Autogpt Platform with a CVSS 3.x base score of 7.7. It is not currently listed as actively exploited by CISA, and its EPSS exploit-prediction score is low. The underlying weakness is classified as CWE-639.

Key facts

Severity: High (CVSS 3.x base score 7.7)
EPSS exploit prediction: 0% (37th percentile)
Actively exploited: Not listed in CISA KEV
EU (EUVD) id: EUVD-2025-23154
Weakness: CWE-639
Affected product: Agpt Autogpt Platform
Published: 2025-07-30
Last modified: 2026-06-17

Description

AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's get_graph_execution_results endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graph_id, it fails to verify ownership of the graph_exec_id parameter, allowing authenticated users to access any execution results by providing arbitrary execution IDs. The internal API implements proper validation for both parameters. This is fixed in v0.6.16.

Frequently asked questions

What is CVE-2025-53944?: AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents. In v0.6.15 and below, the external API's get_graph_execution_results endpoint has an authorization bypass vulnerability. While it correctly validates user access to the graph_id, it fails to verify ownership of the graph_exec_id parameter, allowing authenticated users to access any execution results by providing arbitrary execution IDs. The internal API implements proper validation for both parameters. This is fixed in v0.6.16.
How severe is CVE-2025-53944?: CVE-2025-53944 has a CVSS 3.x base score of 7.7, rated high severity. It is exploitable over network with low attack complexity, requires low privileges and no user interaction. Impact on confidentiality is high, integrity none, and availability none.
Is CVE-2025-53944 being actively exploited?: It is not currently listed in CISA's KEV catalog. Its EPSS exploit-prediction score is 0% (37th percentile), an estimate of the probability of exploitation in the next 30 days.
What products are affected by CVE-2025-53944?: CVE-2025-53944 affects Agpt Autogpt Platform. See the affected-products list for the exact vulnerable versions.
How do I fix CVE-2025-53944?: Review the linked vendor and NVD advisories for patched versions and mitigations, then upgrade or apply the recommended workaround. Given its high severity, prioritise patching exposed systems.
Does CVE-2025-53944 have an EU (EUVD) identifier?: Yes. CVE-2025-53944 is tracked in the ENISA EU Vulnerability Database (EUVD) as EUVD-2025-23154.
When was CVE-2025-53944 published?: CVE-2025-53944 was published on 2025-07-30 and last updated on 2026-06-17.

References

Affected products (1)

cpe:2.3:a:agpt:autogpt_platform:0.6.13:beta:*:*:*:*:*:*

More vulnerabilities in Agpt Autogpt Platform

CVE-2025-62616 — Critical (CVSS 9.8): AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that…
CVE-2025-62615 — Critical (CVSS 9.8): AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that…
CVE-2026-26020 — High (CVSS 8.8): AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that…
CVE-2026-24780 — High (CVSS 8.8): AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that…
CVE-2025-1040 — High (CVSS 8.8): AutoGPT versions 0.3.4 and earlier are vulnerable to a Server-Side Template Injection (SSTI) that could lead to Remote…
CVE-2025-31491 — High (CVSS 8.6): AutoGPT is a platform that allows users to create, deploy, and manage continuous artificial intelligence agents that…

All CVEs affecting Agpt Autogpt Platform →

Other CWE-639 (Authorization Bypass Through User-Controlled Key (IDOR)) vulnerabilities

CVE-2025-40805 — Critical (CVSS 10.0): Affected devices do not properly enforce user authentication on specific API endpoints. This could facilitate an…
CVE-2024-45032 — Critical (CVSS 10.0): A vulnerability has been identified in Industrial Edge Management Pro (All versions < V1.9.5), Industrial Edge…
CVE-2026-62283 — Critical (CVSS 9.9): Nezha Monitoring is a self-hostable, lightweight, servers and websites monitoring and O&M tool. Nezha versions 1.14.13…
CVE-2026-73656 — Critical (CVSS 9.9): Trigger.dev is a platform for building and deploying fully managed AI agents and workflows. Prior to 4.5.6, POST…
CVE-2026-48765 — Critical (CVSS 9.9): TypeBot is a chatbot builder tool. Versions prior to 3.17.0 allow a low-privilege read collaborator to extract a…
CVE-2026-67622 — Critical (CVSS 9.9): Flowise through 3.1.4 contains an insecure direct object reference vulnerability in the OpenAI Assistants integration…

Browse all CWE-639 (Authorization Bypass Through User-Controlled Key (IDOR)) vulnerabilities →