AgentFlayer 0-click exploit abuses ChatGPT Connectors to Steal 3rd-party app data
AgentFlayer is a critical vulnerability in ChatGPT Connectors. Learn how this zero-click attack uses indirect prompt injection to…
ai
Cyber Commandos To Spot And Prevent Artificial Intelligence-Driven Offences
The Union Ministry of Home Affairs has initiated training for specialised "cyber commandos" to effectively combat the rising tide of AI-driven cybercrimes.As cybercriminals increasingly leverage artificial intelligence for sophisticated attacks, these commandos will be equipped to identify, intercept, and neutralise such threats.The training, conducted at the Defence Institute of Advanced
Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise
Researchers demonstrate how multi-turn “storytelling” attacks bypass prompt-level filters, exposing systemic weaknesses in GPT-5’s defenses.
The post Red Teams Jailbreak GPT-5 With Ease, Warn It’s ‘Nearly Unusable’ for Enterprise appeared first o…
ChatGPT-5 Release and Uses in the Legal Industry
OpenAI released ChatGPT-5 today, introducing a range of new features that could offer significant benefits to legal professionals. The company describes improvements in reasoning, speed, and the ability to process very large amounts of information at once. If these capabilities work as designed, law firms and in-house counsel could potentially review entire case files, including […]
The post ChatGPT-5 Release and Uses in the Legal Industry appeared first on TCDI.
China-Pakistan Join Forces Under CENTAIC; Should India Be Concerned?
The China-Pakistan CENTAIC (Centre for Artificial Intelligence and Computing) represents a significant deepening of military collaboration between the two countries, particularly in the domain of AI-enabled warfare.Established by the Pakistan Air Force (PAF) in 2020 under the National Aerospace Science & Technology Park (NASTP) initiative, CENTAIC focuses on developing AI tools for
Gemini AI Exploited via Google Invite Prompt Injection to Steal Sensitive User Data
Security researchers have discovered a series of critical vulnerabilities in Google’s Gemini AI assistant that allow attackers to exploit the system through seemingly innocent Google Calendar invitations and emails, potentially compromising users…
Microsoft unveils Project Ire: AI that autonomously detects malware
Microsoft’s Project Ire uses AI to autonomously reverse engineer and classify software as malicious or benign. Microsoft announced Project Ire, an autonomous artificial intelligence (AI) system that can autonomously reverse engineer and classify software. Project Ire is an LLM-powered autonomous malware classification system that uses decompilers and other tools, reviews their output, and determines the […]
China Accuses Nvidia of Putting Backdoors into Their Chips
The government of China has accused Nvidia of inserting a backdoor into their H20 chips:
China’s cyber regulator on Thursday said it had held a meeting with Nvidia over what it called “serious security issues” with the company’s…
New Promptware Attack Hijacks User’s Gemini AI Via Google Calendar Invite
Cybersecurity researchers demonstrate a new attack on Google Gemini AI for Workspace. Discover how a simple calendar invite can be used to perform phishing, steal emails, and even control home appliances.
Dhruva Space To Deploy Two Australian Payloads Using Its Home-Built Satellite Platform
Dhruva Space, a Hyderabad-based Indian private space start-up, is poised to carry out its first commercial satellite mission, LEAP-1, targeted for launch in the third quarter of 2025. The mission, notable for its international collaboration, will deploy advanced payloads from two Australian firms—Akula Tech and Esper Satellites—using Dhruva’s indigenously developed P-30 satellite platform,