VulnerabilityPublished 19 Feb 2026Updated 23 Feb 2026

CVE-2025-41023: Thesamur AutoGPT · Improper Authentication

Affects Thesamur AutoGPTSource CVE Database V5

Not known to be exploited · CVSS 6.9 Medium.

Data as of 26 Oct 2026, 17:16 UTC

CVSS 4.0 base score

6.9Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.5% chance of exploitation in 30 days – higher than 46% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.

CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:L/VI:L/VA:N/SC:N/SI:N/SA:N

Attack Vector: Network
Attack Complexity: Low
Attack Requirements: None
Privileges Required: None
User Interaction: None
Vulnerable system confidentiality: Low
Vulnerable system integrity: Low
Vulnerable system availability: None
Subsequent system confidentiality: None
Subsequent system integrity: None
Subsequent system availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable system is bound to the network stack and the set of possible attackers extends beyond the other options listed below, up to and including the entire Internet. Such a vulnerability is often termed “remotely exploitable” and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: The attacker must take no measurable action to exploit the vulnerability. The attack requires no target-specific circumvention to exploit the vulnerability. An attacker can expect repeatable success against the vulnerable system.
Attack Requirements: None: The successful attack does not depend on the deployment and execution conditions of the vulnerable system. The attacker can expect to be able to reach the vulnerability and execute the exploit under all or most instances of the vulnerability.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files of the vulnerable system to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without interaction from any human user, other than the attacker.
Vulnerable system confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the Vulnerable System.
Vulnerable system integrity: Low: Modification of data is possible, but the attacker does not have control over the consequence of a modification, or the amount of modification is limited. The data modification does not have a direct, serious impact to the Vulnerable System.
Vulnerable system availability: None: There is no impact to availability within the Vulnerable System.
Subsequent system confidentiality: None: There is no loss of confidentiality within the Subsequent System or all confidentiality impact is constrained to the Vulnerable System.
Subsequent system integrity: None: There is no loss of integrity within the Subsequent System or all integrity impact is constrained to the Vulnerable System.
Subsequent system availability: None: There is no impact to availability within the Subsequent System or all availability impact is constrained to the Vulnerable System.

Definitions: FIRST CVSS v4.0 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 19 Feb 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 26 Oct 2026.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC or the CVSS exploit maturity reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Affected software

Product	Affected	Fixed in
ThesamurAutoGPT	Affected =All versions	Fixed in–

AI-suggested

Until an official patch is released by Thesamur, organizations should implement strict network segmentation to isolate AutoGPT instances from critical infrastructure and sensitive data stores. Employ robust access control lists (ACLs) and firewall rules to restrict inbound traffic to trusted IP addresses only. Monitor application logs and network traffic for unusual access patterns or unauthorized feature usage indicative of exploitation attempts. Consider deploying Web Application Firewalls (WAFs) with custom rules to detect and block suspicious requests targeting authentication endpoints. Conduct regular security assessments and penetration testing focused on authentication mechanisms to identify potential bypasses. Limit the exposure of AutoGPT interfaces to internal networks or VPNs rather than public internet access. Educate security teams about this vulnerability to ensure rapid detection and response. Once patches become available, prioritize immediate deployment and verify their effectiveness through testing. Additionally, review and harden related infrastructure components to reduce attack surface and prevent lateral movement.

Description

An authentication bypass vulnerability has been found in Thesamur's AutoGPT. This vulnerability allows an attacker to bypass authentication mechanisms. Once inside the web application, the attacker can use any of its features regardless of the authorisation method used.

Impact

The authentication bypass allows attackers to gain unauthorized access to all functionalities of the AutoGPT web application, potentially compromising sensitive data and automated processes managed by the software. Organizations relying on AutoGPT for AI automation could face data breaches, unauthorized command execution, or manipulation of automated tasks, leading to operational disruptions. Since the vulnerability requires no authentication or user interaction, exploitation is straightforward and can be performed remotely, increasing the risk of widespread attacks. The medium CVSS score reflects moderate impact on confidentiality and integrity but no direct impact on availability. However, the full access granted could facilitate further attacks within the network, such as privilege escalation or lateral movement. The absence of known exploits in the wild currently limits immediate threat but does not diminish the urgency for mitigation. Industries heavily dependent on AI automation, including technology, finance, healthcare, and manufacturing, may experience significant operational and reputational damage if exploited.

Summary

CVE-2025-41023 identifies a critical security flaw in Thesamur's AutoGPT product, affecting all released versions. The vulnerability is an authentication bypass categorized under CWE-287, meaning the application fails to properly verify user credentials before granting access. This flaw enables an attacker to access the web application and utilize any of its features without undergoing any authentication or authorization checks. The CVSS 4.0 vector indicates that the attack can be launched remotely (AV:N) with low attack complexity (AC:L), requiring no privileges (PR:N) or user interaction (UI:N). The impact on confidentiality and integrity is low to medium (VC:L, VI:L), with no effect on availability (VA:N). The scope remains unchanged (S:N), and no security requirements are bypassed (SI:N, SA:N). Although no patches are currently available and no exploits have been observed in the wild, the vulnerability's nature means that once exploited, an attacker gains full control over the application features, potentially leading to unauthorized data access, manipulation, or further lateral movement within an organization’s environment. The vulnerability was reserved in April 2025 and published in February 2026 by INCIBE, reflecting a responsible disclosure process. Given AutoGPT's role in AI-driven automation, this vulnerability could be leveraged to disrupt automated workflows or exfiltrate sensitive data processed by the application.

CWE-287Improper Authentication (opens in a new tab)
Class weaknessLikelihood of exploit: HighOWASP Top 10 A07:2025: Authentication Failures (opens in a new tab)
When an actor claims to have a given identity, the product does not prove or insufficiently proves that the claim is correct.
MITRE discourages mapping vulnerabilities to this broad entry; the root cause is usually a more specific weakness.
Architecture and Design · Libraries or Frameworks
Use an authentication framework or library such as the OWASP ESAPI Authentication feature.
OWASP Cheat Sheets
OWASP Authentication (opens in a new tab)
OWASP ASVS 4.0.3
V2.8.5 (opens in a new tab)
V2.8.4 (opens in a new tab)
V9.2.3 (opens in a new tab)
Attack patterns
Fake the Source of Data (opens in a new tab)
Utilizing REST's Trust in the System Resource to Obtain Sensitive Data (opens in a new tab)
Session Hijacking (opens in a new tab)
Token Impersonation (opens in a new tab)
Upload a Web Shell to a Web Server (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

incibe.es/en/incibe-cert/notices/aviso/authentication-bypass-autogpt-de-thesamur (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 28 Feb 2026, 13:28 UTC

WeaknessesCWE-287

Technical details

References

Community reviews

Related threats