Lucene search
+L

34 matches found

Kitploit
Kitploit
•added 2026/10/06 7:30 p.m.•17 views

system_prompts_leaks

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...

6AI score
SaveExploits0References23
Kitploit
Kitploit
•added 2026/10/06 2:31 p.m.•16 views

bumblebee

Catálogos de Exposición de Inteligencia de Amenazas Catálogos de exposición mantenidos para campañas recientes de cadena de suministro, construidos a partir de informes públicos de inteligencia de amenazas con Perplexity Computer y actualizados mediante PRs a medida que se reportan nuevas campaña...

6.3AI score
SaveExploits0References14
The Hacker News
The Hacker News
•added 2026/06/30 8:37 a.m.•65 views

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...

5.9AI score
SaveExploits0
Microsoft Secure
Microsoft Secure
•added 2026/06/29 4:27 p.m.•36 views

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...

6AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/06/29 3:40 p.m.•32 views

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...

5.8AI score
SaveExploits0
The Hacker News
The Hacker News
•added 2026/03/11 4:38 p.m.•23 views

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...

6AI score
SaveExploits0
HackRead
HackRead
•added 2026/03/05 5:26 p.m.•23 views

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...

5.9AI score
SaveExploits0
BDU FSTEC
BDU FSTEC
•added 2026/01/14 12:00 a.m.•22 views

The vulnerability of Perplexity AI platform, related to the disclosure of information through query strings, allows a intruder to gain unauthorized access to confidential information.

The vulnerability of the Perplexity AI platform relates to the disclosure of information through query strings. Exploiting this vulnerability could allow a remote attacker to gain unauthorized access to confidential information...

4.3CVSS5.8AI score0.00346EPSS
SaveExploits0References3Affected Software1
HackRead
HackRead
•added 2025/11/29 2:03 p.m.•16 views

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...

6.9AI score
SaveExploits0
Packet Storm News
Packet Storm News
•added 2025/10/28 12:00 a.m.•17 views

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...

6.8AI score
SaveExploits0
HackRead
HackRead
•added 2025/10/17 11:06 a.m.•19 views

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...

7AI score
SaveExploits0
EUVD
EUVD
•added 2025/10/03 8:07 p.m.•16 views

EUVD-2025-21932

Malicious code in bioql PyPI...

7.5CVSS6.6AI score0.00419EPSS
SaveExploits0References3
RedhatCVE
RedhatCVE
•added 2025/09/19 12:29 a.m.•36 views

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

4.3CVSS6.6AI score0.00346EPSS
SaveExploits0References1
NVD
NVD
•added 2025/09/17 2:15 p.m.•15 views

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

4.3CVSS0.00346EPSS
SaveExploits0References2
CNNVD
CNNVD
•added 2025/09/17 12:00 a.m.•13 views

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...

4.3CVSS6.4AI score0.00346EPSS
SaveExploits0References3
Rapid7 Vulnerability Database (full)
Rapid7 Vulnerability Database (full)
•added 2025/09/17 12:00 a.m.•3 views

CVE-2025-50709: Use of GET Request Method With Sensitive Query Strings

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

4.3CVSS5.6AI score0.00346EPSS
SaveExploits0References2
CVE
CVE
•added 2025/09/17 12:00 a.m.•37 views

CVE-2025-50709

A security vulnerability exists in the Perplexity AI platform (specifically involving GPT-4 ) that allows a remote attacker to gain unauthorized access to confidential information . The root cause is the use of a GET parameter containing sensitive query strings, which can lead to information disc...

4.3CVSS6.2AI score0.00346EPSS
SaveExploits0References2
Cvelist
Cvelist
•added 2025/09/17 12:00 a.m.•24 views

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

0.00346EPSS
SaveExploits0References2
Positive Technologies
Positive Technologies
•added 2025/09/17 12:00 a.m.•16 views

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...

4.3CVSS6.2AI score0.00346EPSS
SaveExploits0References4
Vulnrichment
Vulnrichment
•added 2025/09/17 12:00 a.m.•7 views

CVE-2025-50709

An issue in Perplexity AI GPT-4 allows a remote attacker to obtain sensitive information via a GET parameter...

6.2AI score0.00346EPSS
SaveExploits0References2
Rows per page
Query Builder