15 articles tagged with #credential-theft. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers have identified a critical vulnerability in AI infrastructure layers used for cryptocurrency payments, where intermediary systems can intercept sensitive wallet data. The flaw has reportedly enabled credential theft and at least one $500,000 wallet drain, exposing a significant security gap as AI agents become more integrated into crypto transaction systems.
A critical vulnerability in Amazon Q Developer enables attackers to steal cloud credentials through malicious code repositories, exposing organizations to potential data breaches and unauthorized cloud access. The flaw underscores broader security gaps in AI-assisted coding tools that lack adequate safeguards against supply chain attacks.
Zimperium reports that the Rokarolla Android banking trojan is targeting 217 banking and cryptocurrency apps, stealing PINs, patterns, and passwords from infected devices. The malware is distributed via malicious websites disguised as popular apps like TikTok and Google Chrome, giving attackers broad control over compromised devices.
Researchers discovered malicious Wallpaper Engine downloads on Steam Workshop injecting infostealers, backdoors, and account-hijacking malware into gaming systems. The threat targets cryptocurrency holders who use Steam, exploiting the platform's trusted distribution channel to compromise digital assets and personal accounts.
IBM has identified UnregStealer, a sophisticated banking trojan disguised as a Chrome browser extension that is actively targeting Latin American banks while evading detection systems. The malware steals login credentials and poses a significant threat to financial institutions and users in the region.
Microsoft researchers have identified a critical vulnerability in Claude Code where prompt injection attacks could manipulate AI coding agents into exfiltrating sensitive credentials stored in GitHub and development pipelines. This security flaw highlights systemic risks in deploying AI agents with access to production environments and sensitive infrastructure.
Microsoft released a critical security patch for Visual Studio Code addressing a severe vulnerability that could enable attackers to steal GitHub authentication tokens from developers. The swift remediation underscores the importance of security hardening in widely-used developer tools that serve as potential attack vectors for credential compromise.
Researchers demonstrate that LLM agents are vulnerable to credential exfiltration attacks when sensitive data shares context windows with untrusted content, enabling indirect prompt injection. The study proposes three defense mechanisms: activation probes for pre-output detection, honeytokens with calibrated thresholds, and multi-turn leakage accounting to prevent cumulative credential theft across conversations.
Hackers exploited a vulnerability in Meta's AI support chatbot to gain unauthorized access to high-value Instagram handles, which were then stolen and resold before the company patched the security flaw. The incident highlights critical vulnerabilities in AI-driven customer support systems and raises concerns about account security across major social platforms.
Researchers identified 76 confirmed malicious AI agent skills across major marketplaces, with 13.4% of 3,984 analyzed skills containing critical security vulnerabilities. The findings highlight urgent risks as AI agents gain access to sensitive credentials and systems, with malicious payloads still publicly available on platforms like clawhub.ai.
Google's Threat Intelligence Group warns that AI is being weaponized by state-linked hackers and criminal actors to create autonomous malware and zero-day exploits at scale, posing a direct threat to cryptocurrency users relying on standard security measures. This represents a significant escalation in the sophistication and speed of cyberattacks targeting digital assets.
Cybersecurity firm iZOO Logic has identified BankGhost Builder, a malware-as-a-service threat advertised on Telegram that targets over 700 banks globally. The tool enables criminals to steal banking credentials and hijack user accounts, representing a significant evolution in financial cybercrime infrastructure.
Cybercriminals are deploying PHANTOMPULSE malware through compromised Obsidian plugins, targeting cryptocurrency users via social engineering on LinkedIn and Telegram. This attack demonstrates how legitimate developer tools can be weaponized to compromise crypto wallets and assets through sophisticated credential theft campaigns.
UC researchers identified 26 malicious LLM routers designed to steal cryptocurrency credentials from blockchain developers. This discovery reveals a sophisticated attack vector that exploits the growing integration of AI tools in development workflows, posing direct security risks to the crypto ecosystem.
Researcher Chaofan Shou has identified 26 malicious LLM (Large Language Model) routers that are secretly injecting harmful tool calls and stealing credentials from users. This vulnerability represents a significant security risk in AI agent infrastructure, particularly for cryptocurrency and financial applications that rely on these routing systems.
