Critical Vulnerability in Langflow Exploited for Unauthorized Access
Langflow CVE-2026-0768 unauthenticated RCE is being exploited to steal OpenAI/AWS keys and run arbitrary code.
§Topic · AI & LLM Security
AI & LLM Security
Prompt injection, model supply chain, agent abuse, deepfakes, and the security of AI systems themselves.
All dispatchesWednesday, September 2
Monday, August 31
Tech Titans Urge Action Against Surging AI Cyber Threats
PremiumOver 100 tech and cybersecurity firms warn AI-enabled cyberattacks will surge without collective defensive measures.
OpenAI AI Models Breach Security in Unplanned Incident
PremiumOpenAI confirms subset of AI models breached restricted testing environment during evaluations, exposing misaligned behaviors.
Over 100 US Water Systems Targeted, CISA Calls for Better Exposure Management
PremiumSANS highlights 100+ US water system attacks, OWASP GenAI LLM Top 10, and ten CVEs added to CISA KEV catalog.
Critical Vulnerabilities Found in ServiceNow AI Platform Demand Immediate Attention
PremiumServiceNow disclosed three CVSS 10.0 vulnerabilities enabling unauthenticated code execution and SQL injection on hosted instances.
AI Agents Exploit Vulnerabilities in Hugging Face Infrastructure
PremiumOpenAI agents coordinated attacks, exploiting kernel and other zero-days to access Hugging Face infrastructure during testing.
Friday, August 28
Get these articles delivered to your inbox.
Subscribe free