Advertisement
Rogue LLM Endpoints: Data Exposure & RCE Risk for AI Agents
Unverified LLM endpoints pose significant risks, enabling data leakage and potential remote code execution via compromised AI agent sessions.
LLM Persistent Memory and Contextual Integrity Risks
Analysis of new research on LLM contextual integrity, persistent memory risks, and how frontier models leak sensitive user data over time.
LLM API Flaw Exposes Secrets in OpenAI, Anthropic, Google Traces
A flaw in OpenAI, Anthropic, and Google AI APIs allowed researchers to recover hidden reasoning, API keys, and passwords from exposed session logs.
Financial Institutions Expose Customer Data via Cookie Trackers
European and US financial institutions inadvertently expose customer data to ad platforms through website cookie trackers, raising significant privacy and compliance…
SASE AI Blind Spot: Why Packet Inspection Fails Modern Workflows
Enterprise data leakage via generative AI tools and browser extensions exposes critical flaws in traditional SASE models that rely solely on packet inspection.
Squidbleed: Heartbleed-Style Data Exposure in Squid Proxy
A critical flaw dubbed Squidbleed in Squid Proxy, affecting versions 3.5-6.x, enables Heartbleed-style memory leakage exposing user credentials and session data.
Advertisement
OpenClaw AI Agent Vulnerabilities: Code Execution & Data Leakage
New research reveals OpenClaw AI agents can be tricked into executing malicious code or exfiltrating sensitive data via seemingly benign inputs like vCards and location…
Insecure Self-Hosted AI: 1 Million Exposed Services Risks Analyzed
A security scan of 1 million exposed AI services reveals critical vulnerabilities in self-hosted LLM infrastructure and misconfigured model deployments.
OpenSSL: Data Leakage & DoS Vulnerabilities Patched
OpenSSL patches seven vulnerabilities, including a data leakage flaw and multiple denial-of-service risks. Update immediately to secure cryptographic communications.
Securing Shadow AI: How to Discover and Govern Unauthorized SaaS Tools
Learn how security teams can identify shadow AI usage, monitor OAuth grants, and implement governance to prevent corporate data leakage in SaaS environments.