Lucene search
K

45 matches found

The Hacker News
The Hacker News
added 2026/05/27 7:45 a.m.11 views

AI Chatbot Recommendations Redirect Users to Cryptojacking Malware Sites

Microsoft has warned of an active cryptojacking campaign that makes use of artificial intelligence AI chatbot interactions as a mechanism for surfacing malicious download sites. "This emerging delivery technique extends social engineering beyond conventional search results and increases the...

8.8CVSS7.8AI score0.37158EPSS
Exploits6
The Hacker News
The Hacker News
added 2026/05/05 10:30 a.m.11 views

We Scanned 1 Million Exposed AI Services. Here's How Bad the Security Actually Is

While the software industry has made genuine strides over the past few decades to deliver products securely, the furious pace of AI adoption is putting that progress at risk. Businesses are moving fast to self-host LLM infrastructure, drawn by the promise of AI as a force multiplier and the...

6.4AI score
Exploits0
Schneier on Security
Schneier on Security
added 2026/04/13 10:10 a.m.3 views

AI Chatbots and Trust

All the leading AI chatbots are sycophantic, and that's a problem: Participants rated sycophantic AI responses as more trustworthy than balanced ones. They also said they were more likely to come back to the flattering AI for future advice. And critically ­ they couldn't tell the difference betwe...

5.8AI score
Exploits0
Malwarebytes
Malwarebytes
added 2026/03/31 7:40 p.m.2 views

Asking AI for personal advice is a bad idea, Stanford study shows

Stanford computer scientists just proved what therapists already suspected: AI chatbots will agree with almost anything you say to keep you happy. The researchers caught these systems validating dangerous decisions just to maintain user engagement. That's a worrying development, especially given...

5.9AI score
Exploits0
Debian CVE
Debian CVE
added 2026/03/04 6:25 p.m.6 views

CVE-2026-0847

A vulnerability in NLTK versions up to and including 3.9.2 allows arbitrary file read via path traversal in multiple CorpusReader classes, including WordListCorpusReader, TaggedCorpusReader, and BracketParseCorpusReader. These classes fail to properly sanitize or validate file paths, enabling...

8.6CVSS8.7AI score0.0008EPSS
Exploits3
ATTACKERKB
ATTACKERKB
added 2026/03/04 6:25 p.m.6 views

CVE-2026-0847

A vulnerability in NLTK versions up to and including 3.9.2 allows arbitrary file read via path traversal in multiple CorpusReader classes, including WordListCorpusReader, TaggedCorpusReader, and BracketParseCorpusReader. These classes fail to properly sanitize or validate file paths, enabling...

8.6CVSS6.6AI score0.0008EPSS
Exploits3References2
Schneier on Security
Schneier on Security
added 2026/02/25 12:1 p.m.3 views

Poisoning AI Training Data

All it takes to poison AI training data is to create a website: I spent 20 minutes writing an article on my personal website titled "The best tech journalists at eating hot dogs." Every word is a lie. I claimed without evidence that competitive hot-dog-eating is a popular hobby among tech reporte...

5.6AI score
Exploits0
HackRead
HackRead
added 2026/02/07 5:44 p.m.2 views

Firefox Will Give Users an AI Kill Switch for Better Privacy

Not everyone wants AI in their browser. Firefox 148 is introducing easy toggles to disable chatbots and AI tab grouping. Discover how Mozilla is prioritising user choice and privacy in its latest 2026 update...

5.4AI score
Exploits0
HackRead
HackRead
added 2026/01/14 11:49 a.m.3 views

When Does a Chatbot Make Sense in Freshdesk and When It Doesn’t

Customer support teams adopt chatbots to reduce workload, shorten response times, and control costs. Freshdesk makes chatbot deployment…...

7AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/10/16 12:0 a.m.2 views

Improving Cybercrime Detection and Digital Forensics Investigations with Artificial Intelligence

According to a recent EUROPOL report, cybercrime is still recurrent in Europe, and different activities and countermeasures must be taken to limit, prevent, detect, analyze, and fight it. Cybercrime must be prevented with specific measures, tools, and techniques, for example through automated...

6.9AI score
Exploits0
EUVD
EUVD
added 2025/10/03 8:7 p.m.1 views

EUVD-2024-37080

Malicious code in bioql PyPI...

6.5CVSS6.6AI score0.00162EPSS
Exploits0References1
HackRead
HackRead
added 2025/09/01 8:46 p.m.2 views

Hidden Commands in Images Exploit AI Chatbots and Steal Data

Hidden commands in images can exploit AI chatbots, leading to data theft on platforms like Gemini through a…...

7.2AI score
Exploits0
Packet Storm News
Packet Storm News
added 2025/07/14 12:0 a.m.2 views

Exploring User Security and Privacy Attitudes and Concerns toward the Use of General-Purpose LLM Chatbots for Mental Health

Individuals are increasingly relying on large language model LLM-enabled conversational agents for emotional support. While prior research has examined privacy and security issues in chatbots specifically designed for mental health purposes, these chatbots are overwhelmingly "rule-based" offering...

7AI score
Exploits0
Patchstack
Patchstack
added 2025/06/05 1:20 a.m.6 views

WordPress Chaport <= 1.1.6 - Cross Site Scripting (XSS) Vulnerability

Cross Site Scripting XSS Vulnerability discovered by haudayroi - BlueRock in WordPress Plugin Chaport versions = 1.1.6...

5.9CVSS6AI score0.0017EPSS
Exploits0Affected Software1
Packet Storm News
Packet Storm News
added 2025/06/04 12:0 a.m.1 views

Privacy and Security Threat for OpenAI GPTs

Large language models LLMs demonstrate powerful information handling capabilities and are widely integrated into chatbot applications. OpenAI provides a platform for developers to construct custom GPTs, extending ChatGPT's functions and integrating external services. Since its release in November...

6.8AI score
Exploits0
Cvelist
Cvelist
added 2025/05/14 3:23 p.m.12 views

CVE-2025-47777 5ire Client Vulnerable to Cross-Site Scripting (XSS) and Remote Code Execution (RCE)

5ire is a cross-platform desktop artificial intelligence assistant and model context protocol client. Versions prior to 0.11.1 are vulnerable to stored cross-site scripting in chatbot responses due to insufficient sanitization. This, in turn, can lead to Remote Code Execution RCE via unsafe...

9.6CVSS0.02221EPSS
Exploits1References6
Positive Technologies
Positive Technologies
added 2025/05/14 12:0 a.m.1 views

PT-2025-21176 · Electron +1 · Electron +1

Name of the Vulnerable Software and Affected Versions: 5ire versions prior to 0.11.1 Description: The issue is related to stored cross-site scripting in chatbot responses due to insufficient sanitization, which can lead to Remote Code Execution RCE via unsafe Electron protocol handling and expose...

9.6CVSS6.4AI score0.02221EPSS
Exploits1References14
Packet Storm News
Packet Storm News
added 2025/05/07 12:0 a.m.3 views

A Proposal for Evaluating the Operational Risk for ChatBots Based on Large Language Models

The emergence of Generative AI Gen AI and Large Language Models LLMs has enabled more advanced chatbots capable of human-like interactions. However, these conversational agents introduce a broader set of operational risks that extend beyond traditional cybersecurity considerations. In this work, ...

6.9AI score
Exploits0
Malwarebytes
Malwarebytes
added 2025/02/17 8:12 a.m.6 views

A week in security (February 10 &#8211; February 16)

Last week on Malwarebytes Labs: A suicide reveals the lonely side of AI chatbots, with Courtney Brown Lock and Code S06E03 Apple ordered to grant access to users’ encrypted data Phishing evolves beyond email to become latest Android app threat Apple fixes zero-day vulnerability used in "extremely...

7AI score
Exploits0
CNNVD
CNNVD
added 2025/01/30 12:0 a.m.1 views

EmbedAI 安全漏洞

EmbedAI is a platform from EmbedAI that enables users to use their data to create AI chatbots powered by ChatGPT. A security vulnerability exists in EmbedAI version 2.1 and prior versions that stems from improper access control...

7.5CVSS6.7AI score0.00079EPSS
Exploits0References1
Rows per page
Query Builder