Lucene search
+L

8761 matches found

Vulnrichment
Vulnrichment
added 2025/06/16 2:00 a.m.7 views

CVE-2025-6101 letta-ai letta interface.py function_message eval injection

A vulnerability classified as critical has been found in letta-ai letta up to 0.4.1. Affected is the function functionmessage of the file letta/letta/interface.py. The manipulation of the argument functionname/functionargs leads to improper neutralization of directives in dynamically evaluated...

5.5CVSS7.2AI score0.00337EPSS
SaveExploits0References4
hivepro
hivepro
added 2025/06/16 2:00 a.m.18 views

The 48-Hour Exploit Window: Are You Ready?

Running short on time but still want to stay in the know? Well, we’ve got you covered! We’ve condensed all the key takeaways into a handy audio summary. Our AI-driven podcasts are fit for on the go. Click right here to hear it all on CAASM & CDMB Inefficiencies! Forget everything you know about...

8.4CVSS9.5AI score0.9549EPSS
SaveExploits6
CNNVD
CNNVD
added 2025/06/16 12:00 a.m.18 views

letta-ai letta 安全漏洞

Letta-ai letta is a stateful agent framework with memory, inference, and context management in the Letta-ai open source. A security vulnerability exists in letta-ai letta version 0.4.1 and earlier, which stems from a dynamic code evaluation malpractice issue that could lead to the execution of...

5.5CVSS5.9AI score0.00337EPSS
SaveExploits0References5
Positive Technologies
Positive Technologies
added 2025/06/16 12:00 a.m.17 views

PT-2025-25512 · Letta-Ai · Letta-Ai

Name of the Vulnerable Software and Affected Versions: letta-ai letta versions up to 0.4.1 Description: A critical issue has been found in the function function message of the file letta/letta/interface.py. The manipulation of the argument function name/function args leads to improper...

5.5CVSS5.4AI score0.00337EPSS
SaveExploits0References9
NVD
NVD
added 2025/06/14 9:15 a.m.28 views

CVE-2025-4592

The AI Image Lab – Free AI Image Generator plugin for WordPress is vulnerable to Cross-Site Request Forgery in all versions up to, and including, 1.0.6. This is due to missing or incorrect nonce validation on the 'wpz-ai-images' page. This makes it possible for unauthenticated attackers to update...

4.3CVSS0.00138EPSS
SaveExploits0References2
CVE
CVE
added 2025/06/14 8:23 a.m.50 views

CVE-2025-4592

The CVE-2025-4592 entry concerns the WordPress plugin AI Image Lab – Free AI Image Generator. It describes a Cross-Site Request Forgery vulnerability (versions

4.3CVSS4.2AI score0.00138EPSS
SaveExploits0References2
Cvelist
Cvelist
added 2025/06/14 8:23 a.m.41 views

CVE-2025-4592 AI Image Lab – Free AI Image Generator <= 1.0.6 - Cross-Site Request Forgery to API Key Update

The AI Image Lab – Free AI Image Generator plugin for WordPress is vulnerable to Cross-Site Request Forgery in all versions up to, and including, 1.0.6. This is due to missing or incorrect nonce validation on the 'wpz-ai-images' page. This makes it possible for unauthenticated attackers to update...

4.3CVSS0.00138EPSS
SaveExploits0References2
Vulnrichment
Vulnrichment
added 2025/06/14 8:23 a.m.6 views

CVE-2025-4592 AI Image Lab – Free AI Image Generator <= 1.0.6 - Cross-Site Request Forgery to API Key Update

The AI Image Lab – Free AI Image Generator plugin for WordPress is vulnerable to Cross-Site Request Forgery in all versions up to, and including, 1.0.6. This is due to missing or incorrect nonce validation on the 'wpz-ai-images' page. This makes it possible for unauthenticated attackers to update...

4.3CVSS4.2AI score0.00138EPSS
SaveExploits0References2
Patchstack
Patchstack
added 2025/06/14 6:10 a.m.15 views

WordPress AI Image Lab plugin <= 1.0.6 - Cross-Site Request Forgery to API Key Update vulnerability

Cross-Site Request Forgery to API Key Update vulnerability discovered by Kishan Vyas in WordPress Plugin AI Image Lab versions = 1.0.6...

4.3CVSS6.7AI score0.00138EPSS
SaveExploits0References1Affected Software1
Positive Technologies
Positive Technologies
added 2025/06/14 12:00 a.m.11 views

PT-2025-25473 · WordPress · The Ai Image Lab – Free Ai Image Generator

Name of the Vulnerable Software and Affected Versions: The AI Image Lab – Free AI Image Generator plugin for WordPress versions 1.0.0 through 1.0.6 Description: The issue is related to Cross-Site Request Forgery due to missing or incorrect nonce validation on the 'wpz-ai-images' page. This allows...

4.3CVSS6.2AI score0.00138EPSS
SaveExploits0References7
Malwarebytes
Malwarebytes
added 2025/06/13 3:30 p.m.20 views

Your Meta AI chats might be public, and it’s not a bug

Conversations that people are having with the Meta AI app are being exposed publicly, often without the users realizing it, revealing a variety of medical, legal, and private matters. The standalone app and the company's integrations with artificial intelligence AI across its platforms—Facebook,...

6.8AI score
SaveExploits0
HackRead
HackRead
added 2025/06/13 1:30 p.m.25 views

Arsen Launches AI-Powered Vishing Simulation to Help Organizations Combat Voice Phishing at Scale

Paris, France, 13th June 2025, CyberNewsWire...

7.3AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/06/12 1:52 p.m.19 views

New TokenBreak Attack Bypasses AI Moderation with Single-Character Text Changes

Cybersecurity researchers have discovered a novel attack technique called TokenBreak that can be used to bypass a large language model's LLM safety and content moderation guardrails with just a single character change. "The TokenBreak attack targets a text classification model's tokenization...

7.6AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/06/12 1:06 p.m.12 views

AI Agents Run on Secret Accounts — Learn How to Secure Them in This Webinar

AI is changing everything — from how we code, to how we sell, to how we secure. But while most conversations focus on what AI can do, this one focuses on what AI can break — if you're not paying attention. Behind every AI agent, chatbot, or automation script lies a growing number of non-human...

7.2AI score
SaveExploits0
HackRead
HackRead
added 2025/06/12 12:53 p.m.33 views

EchoLeak Zero-Click AI Attack in Microsoft Copilot Exposes Company Data

Aim Labs uncovers EchoLeak, a zero-click AI flaw in Microsoft 365 Copilot that allows data theft via email. Learn how this vulnerability enables sensitive information exfiltration without user interaction and its implications for AI security...

6.7AI score
SaveExploits0
Wiz blog
Wiz blog
added 2025/06/12 11:55 a.m.23 views

Wiz Integrates with NVIDIA Enterprise AI Factory Validated Design

Wiz is now included in the NVIDIA Enterprise AI Factory validated design, integrating with NVIDIA AI to help developers securely build and deploy enterprise AI agents at scale...

7.2AI score
SaveExploits0
The Hacker News
The Hacker News
added 2025/06/12 11:11 a.m.78 views

Zero-Click AI Vulnerability Exposes Microsoft 365 Copilot Data Without User Interaction

A novel attack technique named EchoLeak has been characterized as a "zero-click" artificial intelligence AI vulnerability that allows bad actors to exfiltrate sensitive data from Microsoft 365 M365 Copilot's context sans any user interaction. The critical-rated vulnerability has been assigned the...

9.3CVSS9.2AI score0.08034EPSS
SaveExploits1
The Hacker News
The Hacker News
added 2025/06/12 11:00 a.m.38 views

Non-Human Identities: How to Address the Expanding Security Risk

Human identities management and control is pretty well done with its set of dedicated tools, frameworks, and best practices. This is a very different world when it comes to Non-human identities also referred to as machine identities. GitGuardian's end-to-end NHI security platform is here to close...

7.1AI score
SaveExploits0
Positive Technologies
Positive Technologies
added 2025/06/12 12:00 a.m.14 views

PT-2025-25295

EchoLeak: First-Ever Zero-Click Vulnerability, CVE-2025-3271, Discovered by Aim Labs in Microsoft 365 Copilot AI, Allowed Attackers Steal Sensitive Data Silently, Now Fixed EchoLeak Hackers Microsoft Copilot CopilotAgent MIcrosoft365 @Microsoft @Copilot...

4.8CVSS6.8AI score0.00303EPSS
SaveExploits0References3
NVD
NVD
added 2025/06/11 2:15 p.m.43 views

CVE-2025-32711

Ai command injection in M365 Copilot allows an unauthorized attacker to disclose information over a network...

9.3CVSS0.08034EPSS
SaveExploits1References2
Rows per page
Query Builder