Lucene search
K

4323 matches found

Github Security Blog
Github Security Blog
โ€ขadded 2026/05/14 8:26 p.m.โ€ข11 views

Open WebUI: Sharing models for others to use (read permission) also exposes model details (system prompt leakage)

Summary When setting model permissions so that a group has read access to it, intending for other users to use it, those users also can read the model's system prompt. However users may consider their system prompt confidential, so we consider this a security issue. Compare...

4.3CVSS5.8AI score0.0022EPSS
Exploits1References4Affected Software1
Snyk
Snyk
โ€ขadded 2026/05/14 8:25 p.m.โ€ข9 views

Improper Authorization

Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Improper Authorization via the bypassfilter parameter in the HTTP query string, which is unintentionally exposed in the route handler. An attacker can gain unauthorized access to restricted models by appendin...

5.4CVSS5.8AI score0.00193EPSS
Exploits1References2
OSV
OSV
โ€ขadded 2026/05/14 8:25 p.m.โ€ข6 views

GHSA-JH9G-8JQW-M2QX Open WebUI Exposes System Prompt to Regular User [Non-Admin]

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

6.5CVSS5.7AI score0.00281EPSS
Exploits1References4
Github Security Blog
Github Security Blog
โ€ขadded 2026/05/14 8:25 p.m.โ€ข13 views

Open WebUI Exposes System Prompt to Regular User [Non-Admin]

Summary A regular user non-admin can view the system prompt of the model which is set by an admin. Details When a regular user non-admin logs into the application, a http://IP:8080/api/models? web request is initiated by the application and in response, it reveals the system prompt of available...

6.5CVSS5.7AI score0.00281EPSS
Exploits1References4Affected Software1
Snyk
Snyk
โ€ขadded 2026/05/14 8:25 p.m.โ€ข8 views

Information Exposure

Overview open-webui is an Open WebUI Affected versions of this package are vulnerable to Information Exposure via the api/models endpoint. An attacker can access sensitive system prompt information by sending authenticated requests as a non-admin user. Remediation Upgrade open-webui to version...

7.1CVSS5.8AI score0.00281EPSS
Exploits1References2
CVE
CVE
โ€ขadded 2026/05/14 7:35 p.m.โ€ข17 views

CVE-2026-8596

CVE-2026-8596: The ModelBuilder/Serve path in the Amazon SageMaker Python SDK stores the HMAC signing key in cleartext. A remote, authenticated actor with SageMaker describe API permissions and S3 write access to the model artifact path could extract the key from API responses and forge integrity...

8.5CVSS6.2AI score0.00439EPSS
Exploits0References4
OSV
OSV
โ€ขadded 2026/05/14 5:16 p.m.โ€ข10 views

PYSEC-2026-40

Diffusers is the a library for pretrained diffusion models. Prior to 0.38.0, a trustremotecode bypass in DiffusionPipeline.frompretrained allows arbitrary remote code execution despite the user passing trustremotecode=False or omitting it, which is the default. The vulnerability has three variant...

8.8CVSS6.5AI score0.00685EPSS
Exploits1References1
RedHat Linux
RedHat Linux
โ€ขadded 2026/05/14 1:49 p.m.โ€ข12 views

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.3

Red Hat Enterprise Linux AI 3.3.3 is now available. Red Hatยฎ Enterprise Linuxยฎ AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

8.7CVSS7.2AI score0.0058EPSS
Exploits1References5
RedHat Linux
RedHat Linux
โ€ขadded 2026/05/14 1:48 p.m.โ€ข10 views

Important: Red Hat Security Advisory: Red Hat Enterprise Linux AI 3.3.3

Red Hat Enterprise Linux AI 3.3.3 is now available. Red Hatยฎ Enterprise Linuxยฎ AI is a foundation model platform to seamlessly develop, test, and run Granite family large language models LLMs for enterprise applications...

8.7CVSS7.1AI score0.00485EPSS
Exploits0References3
Schneier on Security
Schneier on Security
โ€ขadded 2026/05/14 11:4 a.m.โ€ข9 views

How Dangerous Is Anthropicโ€™s Mythos AI?

Last month, Anthropic made a remarkable announcement about its new model, Claude Mythos Preview: it was so good at finding security vulnerabilities in software that the company would not release it to the general public. Instead, it would only be available to a select group of companies to scan a...

5.8AI score
Exploits0
Securelist
Securelist
โ€ขadded 2026/05/14 11:0 a.m.โ€ข11 views

Kimsuky targets organizations with PebbleDash-based tools

Over the past few months, we have conducted an in-depth analysis of specific activity clusters of Kimsuky aka APT43, Ruby Sleet, Black Banshee, Sparkling Pisces, Velvet Chollima, and Springtail, a prolific Korean-speaking threat actor. Our research revealed notable tactical shifts throughout...

6.2AI score
Exploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/14 12:0 a.m.โ€ข29 views

Exploiting LLM Agent Supply Chains Via Payload-Less Skills

Autonomous agents powered by Large Language Models LLMs acquire external functionalities through third-party skills available in open marketplaces. Adopting these integrations broadens the potential attack surface, prompting a need for systematic security evaluation. Current auditing mechanisms a...

5.9AI score
Exploits0
Positive Technologies
Positive Technologies
โ€ขadded 2026/05/14 12:0 a.m.โ€ข14 views

PT-2026-41183

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.8.11 Description An internal-only bypass filter parameter is exposed on the '/openai/chat/completions' and '/ollama/api/chat' HTTP endpoints due to FastAPI query string binding. This allows any authenticated user...

5.4CVSS5.8AI score0.00193EPSS
Exploits1References7
Positive Technologies
Positive Technologies
โ€ขadded 2026/05/14 12:0 a.m.โ€ข17 views

PT-2026-41181

Name of the Vulnerable Software and Affected Versions Open WebUI versions prior to 0.8.9 Description When a non-administrative user logs into the application, a web request to the '/api/models?' endpoint is initiated. The response from this request reveals the system prompts of available models...

6.5CVSS5.8AI score0.00281EPSS
Exploits1References6
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/14 12:0 a.m.โ€ข11 views

Detecting Privilege Escalation in Polyglot Microservices Via Agentic Program Analysis

Microservices are widely adopted in modern cloud systems due to their scalability and fault tolerance. However, microservice architectures introduce significant complexity in privilege and permission control, creating risks of privilege escalation where attackers can gain unauthorized access to...

5.8AI score
Exploits0
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/14 12:0 a.m.โ€ข9 views

UGen: An Agentic Framework for Generating Microarchitectural Attack PoCs

Microarchitectural attacks continue to evolve, uncovering new exploitation vectors in modern processors. From a defensive perspective, assessing a system's susceptibility to such attacks remains challenging. Developing functional attack implementations is labor-intensive, requires deep...

6AI score
Exploits0
Positive Technologies
Positive Technologies
โ€ขadded 2026/05/14 12:0 a.m.โ€ข11 views

PT-2026-41118

Name of the Vulnerable Software and Affected Versions Amazon SageMaker Python SDK versions prior to 2.257.2 Amazon SageMaker Python SDK versions prior to 3.8.0 Description Missing integrity verification in the Triton inference handler allows a remote authenticated actor with S3 write access to th...

7.2CVSS6.2AI score0.0039EPSS
Exploits0References10
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/14 12:0 a.m.โ€ข9 views

MetaBackdoor: Exploiting Positional Encoding As a Backdoor Attack Surface in LLMs

Backdoor attacks pose a serious security threat to large language models LLMs, which are increasingly deployed as general-purpose assistants in safety- and privacy-critical applications. Existing LLM backdoors rely primarily on content-based triggers, requiring explicit modification of the input...

5.8AI score
Exploits0
CNNVD
CNNVD
โ€ขadded 2026/05/13 12:0 a.m.โ€ข7 views

ELECOMๅคšๆฌพไบงๅ“ ่ทจ็ซ™่„šๆœฌๆผๆดž

ELECOM WAB-MAT, among others, are products of the ELECOM company. ELECOM WAB-MAT is a management tool for enterprise access points. ELECOM WAB represents a series of wireless access points. ELECOM WAB-S300 is a wireless access point. Several ELECOM products have cross-site scripting...

4.8CVSS6.3AI score0.00161EPSS
Exploits0References1
Packet Storm News
Packet Storm News
โ€ขadded 2026/05/13 12:0 a.m.โ€ข11 views

Identifying AI Web Scrapers Using Canary Tokens

From pre-training to query-time augmentation, web-scraped data helps to improve the quality and contextual relevancy of content generated by large language models LLMs. However, large-scale web scraping to feed LLMs can affect site stability and raise legal, privacy, or ethics concerns. If websit...

5.7AI score
Exploits0
Rows per page
Query Builder