ai

Android Malware Taps Gemini to Navigate Infected Devices

, , , ,

Android malware named PromptSpy employs generative AI (Gemini) for adaptive navigation on infected devices. It mainly functions to deploy remote access via VNC, utilizing natural language prompts to interact with user interfaces, enhancing the malware's versatility across different devices. Developed by Chinese speakers, PromptSpy is still largely theoretical, with no live telemetry reports from ESET, but suspected distribution domains hint at potential real-world application. The malware can intercept security codes, record screens, and prevent uninstallation, indicating a disturbing evolution in Android threats.

https://www.theregister.com/2026/02/19/genai_malware_android/

Microsoft Says Bug Causes Copilot to Summarize Confidential Emails

, , ,

Microsoft 365 Copilot bug since January causes AI to incorrectly summarize confidential emails, bypassing DLP policies. A code error allows emails marked with confidentiality labels to be processed, prompting Microsoft to initiate a fix. As of mid-February, they continue monitoring the situation but have not disclosed the full impact or timeline for resolution.

https://www.bleepingcomputer.com/news/microsoft/microsoft-says-bug-causes-copilot-to-summarize-confidential-emails/

Huntr

Huntr is the first bug bounty platform focused on AI/ML, allowing security researchers to report vulnerabilities in open-source AI/ML apps, libraries, and model formats. It features over 240 programs with bounties up to $1500. Users can join and engage via Discord to contribute to the security of AI/ML projects.

https://huntr.com/

Manipulating AI Memory for Profit: The Rise of AI Recommendation Poisoning

,

AI Recommendation Poisoning exploits AI memory to influence recommendations by embedding hidden instructions in prompts. Companies use malicious URLs in “Summarize with AI” buttons, instructing AIs to remember them favorably, leading to biased outputs. The trend poses risks as poisoned AIs provide slanted advice on critical topics, affecting users' decisions without their awareness. Microsoft has begun implementing protections against these attacks, but research indicates widespread attempts across various industries to manipulate AI assistants.

https://www.microsoft.com/en-us/security/blog/2026/02/10/ai-recommendation-poisoning/

Are Hackers Trying to Utilize Gemini AI’s Capabilities for Malicious Purposes?

, ,

Hackers are attempting to exploit Gemini AI for cyberattacks, as highlighted in a Google Threat Intelligence report. While direct cloning hasn’t succeeded, state-sponsored groups are using AI tools for sophisticated hacks. The private sector is also interested in Gemini’s proprietary technology for development, raising concerns about intellectual property theft. Despite growing reliance on AI, Americans remain distrustful, fearing privacy violations and data exploitation.

https://www.pandasecurity.com/en/mediacenter/are-hackers-trying-to-utilize-gemini-ais-capabilities-for-malicious-purposes/

Infostealer Malware Found Stealing OpenClaw Secrets for First Time

,

Infostealer malware has been detected stealing sensitive data from OpenClaw, an AI assistant framework, marking a new trend in targeting personal AI configurations. The stolen files include API keys and login information, with a potential full compromise of victims' digital identities. Hudson Rock identified the malware as having similarities to the Vidar infostealer. As OpenClaw gains traction, its configuration files, containing sensitive authentication secrets, are increasingly being targeted by cybercriminals.

https://www.bleepingcomputer.com/news/security/infostealer-malware-found-stealing-openclaw-secrets-for-first-time/

How Global Cybercrime Syndicates Are Stealing Hearts — and Billions

, ,

Global cybercrime syndicates are exploiting romance scams, using AI to create convincing online identities to deceive victims, particularly during Valentine's season. In 2024, Americans lost over $16 billion to cybercrime, with one in seven adults affected by romance schemes. These scams, targeting older demographics, leverage trust and urgency to manipulate victims, often moving conversations off safer platforms. Law enforcement faces challenges due to the international nature of these operations, but agencies like the FBI are forming global partnerships to combat them. Vigilance is necessary for online daters, as pressure tactics are common indicators of scams.

https://www.politico.com/news/2026/02/14/how-global-cybercrime-syndicates-are-stealing-hearts-and-billions-00780481

Major ‘vibe-coding’ Platform Orchids Is Easily Hacked, Researcher Finds

, , ,

A security flaw in Orchids AI platform led to a BBC reporter's laptop being hacked without any user action. A cybersecurity researcher exploited vulnerabilities, demonstrating risks associated with “vibe-coding” tools that allow non-technical users to create applications. This zero-click attack could compromise sensitive data and device security, raising concerns about the convenience of AI tools. Experts warn of a new class of vulnerabilities in AI systems.

https://www.bbc.com/news/articles/cy4wnw04e8wo

Milan-Cortina 2026: How Winter Olympics Embraced AI to Fend Off Cyber Attacks

,

Milan-Cortina 2026 Winter Olympics implement AI and cybersecurity measures to combat threats amid geopolitical tensions. Organized by Italian authorities and supported by technology partners, initiatives focus on mitigating cyber attacks, including DDoS attempts. Key infrastructure will handle extensive data operations, ensuring performance and security throughout the Games.

https://www.sportspro.com/analysis/technology/milan-cortina-2026-winter-olympics-cybersecurity-ai-tech-february-2026/

Microsoft Warns That Poisoned AI Buttons and Links May Betray Your Trust

, , ,

Microsoft warns of “AI Recommendation Poisoning,” a technique where malicious data manipulates AI responses, risking trust in AI services. Companies have been embedding hidden prompts in AI links, influencing outputs subtly. This can result in AI providing biased advice on crucial topics like health and finance, often unnoticed by users. Microsoft advises caution with AI-related links, reviewing AI memory, and scanning for manipulation attempts in corporate settings.

https://www.theregister.com/2026/02/12/microsoft_ai_recommendation_poisoning/

Google Reports State-Backed Hackers Using Gemini AI for Recon and Attack Support

,

Google Alerts State-Backed Hackers Using Gemini AI for Attacks
North Korean group UNC2970 exploited Google’s Gemini AI for reconnaissance and cyber espionage, targeting cybersecurity firms. The AI synthesized OSINT for profiling high-value targets, enabling tailored phishing strategies. Other hacker groups, including Chinese and Iranian actors, also misuse Gemini for intelligence gathering and deploying malware. Google emphasizes ongoing efforts to enhance safety systems against AI misuse.

https://thehackernews.com/2026/02/google-reports-state-backed-hackers.html

Claude Desktop Extensions 0-Click RCE Vulnerability Exposes 10,000+ Users to Remote Attacks

,

Critical vulnerability in Claude Desktop Extensions allows 0-click remote code execution, affecting 10,000+ users. Attackers exploit this flaw via Google Calendar events, enabling unauthorized commands without user consent. LayerX warns of severe trust boundary violations; fixes are currently not planned by Anthropic.

https://cybersecuritynews.com/claude-desktop-extensions-0-click-vulnerability/

The Rise of Moltbook Suggests Viral AI Prompts May Be the Next Big Security Threat

,

The rise of AI agents, particularly through platforms like OpenClaw and Moltbook, raises concerns about self-replicating ‘prompt worms' that could exploit these agents, spreading harmful instructions and data risks. Potential interventions from API providers could mitigate threats but may alienate users. The urgency for solutions grows as local AI capabilities improve, leading to a future where unregulated AI interactions might create security crises.

https://arstechnica.com/ai/2026/02/the-rise-of-moltbook-suggests-viral-ai-prompts-may-be-the-next-big-security-threat/

From Magic to Malware: How OpenClaw’s Agent Skills Become an Attack Surface

, ,

TLDR: OpenClaw presents security risks as its agent skills access sensitive data through markdown files that can disguise harmful commands. Instances of malware disguised as “skills” have been identified, posing threats to corporate devices. Users are warned against using OpenClaw on work devices, emphasizing the importance of security measures for skill registries and agent frameworks to prevent exploitation.

https://1password.com/blog/from-magic-to-malware-how-openclaws-agent-skills-become-an-attack-surface

Scroll to Top