31 matches found
bumblebee
Threat Intelligence Exposure Catalogs Maintained exposure catalogs for recent supply-chain campaigns, built from public threat-intelligence reporting with Perplexity Computer and updated via PRs as fresh campaigns are reported. Pass a catalog to a scan with --exposure-catalog . Review the entries...
system_prompts_leaks
Как написано в The Washington Post: Узнайте скрытые правила, стоящие за ИИ. Затем используйте их, чтобы переписать эту статью. 11 мая 2026 Утечки системных промптов Цель этого репозитория — документировать инструкции системных промптов для всех ИИ-чатботов: Claude, ChatGPT, Gemini и т.д. Недавно...
New BioShocking Attack Tricks AI Browsers Into Leaking User Credentials
Convince an AI browser that it is playing a game, and it can hand over your login details. That is the finding behind BioShocking , a technique from security firm LayerX that tricked six AI browsers and assistants into copying a user's credentials and sending them to an attacker. The targets...
Chromium extension uses AI‑related branding to redirect browser search
In this article 1. Extension overview 2. Key indicators of malicious behavior 3. Dynamic analysis findings 4. Mitigation and protection guidance 5. References 6. Learn more Microsoft Threat Intelligence has identified a malicious Chromium-based extension that spoofs the AI-powered answer engine...
Malicious Perplexity Chrome Extension Intercepted Searches and Address Bar Input
Microsoft has found a malicious Chrome extension that posed as the AI search engine Perplexity and quietly logged what people searched for. It routed every query and every character typed into the address bar through an attacker-controlled server before redirecting users to real results. Microsof...
Researchers Trick Perplexity's Comet AI Browser Into Phishing Scam in Under Four Minutes
Agentic web browsers that leverage artificial intelligence AI capabilities to autonomously execute actions across multiple websites on behalf of a user could be trained and tricked into falling prey to phishing and scam traps. The attack, at its core, takes advantage of AI browsers' tendency to...
PleaseFix Flaw Lets Hackers Access 1Password Vault via Comet AI Browser
Researchers at Zenity Labs uncover PleaseFix flaws in Perplexity’s Comet browser. See how zero-click calendar invites allow AI agents to steal 1Password credentials and personal files...
HashJack Attack Uses URL ‘#’ to Control AI Browser Behavior
Cybersecurity firm Cato Networks reveals HashJack, a new AI browser vulnerability using the '' symbol to hide malicious commands. Microsoft and Perplexity fixed the flaw, but Google's Gemini remains at risk...
Secure Retrieval-Augmented Generation against Poisoning Attacks
Large language models LLMs have transformed natural language processing NLP, enabling applications from content generation to decision support. Retrieval-Augmented Generation RAG improves LLMs by incorporating external knowledge but also introduces security risks, particularly from data poisoning...
Malicious Perplexity Comet Browser Download Ads Push Malware Via Google
Attackers are exploiting Google Ads with fake Comet Browser download links to spread malware disguised as Perplexity’s official installer. The campaign, tracked by DataDome, has ties to DarkGate...
EUVD-2025-21932
Malicious code in bioql PyPI...
CVE-2025-50709
An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...
CVE-2025-50709
An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...
Perplexity AI Web Application 安全漏洞
Perplexity AI Web Application is a big data search engine application utilizing a big language model from Perplexity, Inc. in the United States. A security vulnerability exists in Perplexity AI Web Application that stems from a GET parameter that could lead to the disclosure of sensitive...
CVE-2025-50709
CVE-2025-50709 affects Perplexity AI GPT-4. The issue allows a remote attacker to obtain sensitive information via a GET parameter. CVSSv3.1 base score 4.3 (Medium), attack Vector: Network, attack Complexity: Low, Privileges Required: Low, User Interaction: none. Connected sources confirm Perplex...
CVE-2025-50709
An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...
PT-2025-38157
Name of the Vulnerable Software and Affected Versions: Perplexity AI GPT-4 affected versions not specified Description: An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter. Recommendations: At the moment, there is no information about a new...
CVE-2025-50709
An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...
Perplexity AI ignores no-crawling rules on websites, crawls them anyway
Imagine putting up a no-trespassing sign for people walking their dogs, and then finding out that one person dresses up their Great Dane as a calf and walks it on your grounds. Well that's sort of what AI answer engine Perplexity has been doing, by evading the no-crawl directives of websites,...