Advertisement
OpenAI GPT-5.6 Sol Rollout: Technical Safeguards and Cyber Risk Mitigation
OpenAI limits the GPT-5.6 Sol rollout, introducing enhanced cyber safeguards and restricted access protocols to mitigate AI-driven security threats.
Securing AI Agent Identities: Mitigating Risks in LLM Deployments
Explore the identity problem in AI agent deployments and learn how to secure non-human identities and service accounts used by autonomous AI systems.
Dify AI Platform Vulnerabilities: How to Mitigate DifyTap Exploit
Researchers discover DifyTap vulnerabilities in the Dify AI platform, allowing attackers to exfiltrate chat histories and secrets through SSRF and RCE.
AutoJack: AI Browsing Agents Hijacked for Host RCE via Web Pages
Microsoft researchers reveal AutoJack, a novel exploit chain where malicious web pages hijack AI browsing agents to achieve remote code execution on host systems.
Malicious JetBrains Plugins Steal AI API Keys: Supply Chain Risks
Researchers discovered 15 malicious plugins on the JetBrains Marketplace designed to exfiltrate sensitive AI API keys from developers' IDE environments.
CVE-2024-5027: Langflow Path Traversal Exploited in Attacks
Security researchers observe active exploitation of CVE-2024-5027, a high-severity path traversal flaw in the Langflow AI platform allowing arbitrary file writes.
Anthropic Project Glasswing: AI Vulnerability Discovery Challenges
Anthropic's Project Glasswing identifies 23,000 potential vulnerabilities via the Mythos AI model, highlighting the massive gap between discovery and patching.
Optimizing AI-Powered Security Operations Platforms for SOC Value
Analysis of why only 10% of SOC teams report excellent value from AI tools and how to improve security operations through second-wave agentic AI integration.
Military AI Integration: Strategic Risks and Technical Guardrails
Analyze the Pentagon's acceleration of battlefield AI and the technical risks of autonomous systems, highlighting the need for human-centric oversight.
Shadow AI Risks: Securing Production against Exposed Vibe-Coded Apps
Analysis of the 'Shadow Builders' report identifying 2,000 exposed AI-generated apps and the critical security gaps in AI-assisted software development.
Anthropic Claude Mythos-Class Models: Security Implications of Public Rollout
Anthropic confirms public rollout plans for Claude Mythos-class models, addressing previous delays caused by software security risks and safety concerns.
Geordie Secures $30M for AI Security and Governance Platform
Geordie raises $30M in Series A funding to address enterprise AI security risks, focusing on governance, visibility, and data protection for LLM deployments.