system_prompts_leaks — Updated!

Thanks to Open Source Agent Analytics Understand your agents in production System Prompts Leaks The full verbatim system prompts behind the most popular chatbots in the world. Carefully curated and complete. Feel free to open up a PR or get in contact if you got a different result. The Washington...

Forget the AI Slowdown—the Vulnerability Explosion Is Already Happening

AI labs are toying with an industry-wide pact to slow development. Meanwhile, widely available AI chatbots are already helping uncover a tidal wave of security flaws...

chatting-chatbots (0.0.1), embedding-lenses (>=0.1.0, <=0.11.0) +3 more potentially affected by CVE-2026-66007 via datasets (1.14.0)

datasets PYPI version 1.14.0 is affected by a known vulnerability. The following packages have a transitive dependency on datasets and may be impacted: - chatting-chatbots 0.0.1 - embedding-lenses =0.1.0, =1.2.0, =0.3.0, =0.3.3 - zensols-mednlp 0.0.1 Source cves: CVE-2026-66007 Source advisory:...

Meta Contractors Posed as Teens to Prompt Rival Chatbots About Suicide, Sex, and Drugs

Hundreds of contractors working on a project for Meta pretended to be kids in order to see how other chatbots like Gemini and ChatGPT would respond to high-risk subjects, WIRED found...

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...

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...

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...

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...

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...

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...

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...

CVE-2025-12448: Improper Neutralization of Input During Web Page Generation

The Smartsupp – live chat, AI shopping assistant and chatbots plugin for WordPress is vulnerable to Stored Cross-Site Scripting via the 'code' parameter in all versions up to, and including, 3.9.1 due to insufficient input sanitization and output escaping. This makes it possible for authenticated...

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...

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…...

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...

EUVD-2024-37080

Malicious code in bioql PyPI...

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…...

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...

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...

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...