Cyber Resilience

CVE-2025-53944

HighPublic PoC

Published: 30 July 2025

Published
30 July 2025
Modified
05 August 2025
KEV Added
Patch
CVSS Score v3.1 7.7 CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
EPSS Score 0.0049 65.8th percentile
Risk Priority 16 60% EPSS · 20% KEV · 20% CVSS

Summary

CVE-2025-53944 is a high-severity Improper Authorization (CWE-285) vulnerability in Agpt Autogpt Platform. Its CVSS base score is 7.7 (High).

Operationally, exploitation aligns with the MITRE ATT&CK technique Exploitation for Privilege Escalation (T1068); ranked in the top 34.2% of CVEs by exploit likelihood; it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.

This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Supply Chain and Deployment risk domain.

EU & UK References

Vulnerability details

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…

more

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.

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 TechniquesAI

T1068 Exploitation for Privilege Escalation Privilege Escalation
Adversaries may exploit software vulnerabilities in an attempt to elevate privileges.
T1213 Data from Information Repositories Collection
Adversaries may leverage information repositories to mine valuable information.
Why these techniques?

Authorization bypass allows authenticated users to access unauthorized execution results (IDOR), enabling exploitation for privilege escalation (T1068) and collection from an enterprise application data repository (T1213).

Affected Assets

agpt
autogpt platform
0.6.13

Mitigating Controls

Likely Mitigating Controls AI

Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.

addresses: CWE-285 CWE-639

The control mandates authorization decisions for each access request, reducing the ability to exploit improper authorization weaknesses.

addresses: CWE-285 CWE-639

The control requires checking and applying authorization decisions per policy, preventing improper authorization.

addresses: CWE-285

Documented procedures facilitate correct implementation and ongoing management of authorization decisions.

addresses: CWE-285

Periodic reviews identify and correct flaws in authorization decisions or enforcement.

addresses: CWE-285

The control's documentation requirement reduces improper authorization by ensuring only mission-justified actions bypass authentication.

addresses: CWE-285

Establishing permitted attributes and values, plus auditing changes, ensures authorization decisions are based on correctly managed policy data.

addresses: CWE-285

Explicitly mandates authorizing remote access types before permitting connections, directly mitigating improper authorization.

addresses: CWE-285

The control explicitly requires authorization of each wireless access type prior to permitting connections.

References