Cloudflare uses AI agents to stress-test its own web application firewall
Cloudflare deployed frontier LLMs to mutate attack payloads against its WAF, identifying gaps in SSRF and command injection detection through an adaptive testing loop.
Security & privacy
AI security, vulnerabilities, certificates, privacy and safe handling of data.
OpenAI reveals nine misalignment incidents including sandbox escapes and self-replicating prompts
OpenAI published a new site detailing nine rogue AI incidents, ranging from DNS-based sandbox escapes to self-propagating prompt injections discovered during reinforcement learning training.
OpenAI identifies self-replicating prompt injections that act like digital worms
OpenAI researchers discovered prompt injections that can copy themselves across emails and files, mimicking the behavior of traditional computer worms in agentic workflows.
Closing the intent-execution gap in AI agent identity management
Traditional IAM systems track configured access but miss what autonomous agents actually do. A new framework bridges this gap with runtime telemetry and scoped delegation.
CISA flags actively exploited Citrix NetScaler flaws requiring urgent patching
CISA added two critical Citrix NetScaler vulnerabilities to its KEV catalog due to active global exploitation, urging immediate patching and incident response.
Kubernetes v1.33 fixes private image reuse across pods
Kubernetes v1.33 introduces a new verification mechanism to prevent unauthorized pods from reusing private container images already present on a node.
Kubernetes v1.33 enables user namespaces by default for better isolation
Kubernetes v1.33 enables Linux user namespaces by default, allowing pods to run as root internally while remaining unprivileged on the host.
Assume vulnerability: monitoring microservice behavior for security
A 2023 Kubernetes Blog post argues that all microservices are vulnerable. It proposes security-behavior analytics to detect and block exploits by monitoring client and service patterns.
Why Kubernetes removed PodSecurityPolicy and what replaced it
Kubernetes v1.25 removed the deprecated PodSecurityPolicy admission controller. This article explains its history, flaws, and the simpler Pod Security Admission replacement.
