Tag: AI agent security
A Simple Website Summary Just Exposed the Limits of AI Coding Guardrails
Tom Smith | | agentic AI security, AI agent security, AI coding assistants, AI guardrails, AI security, Anthropic, Auto Mode, Claude Code, Claude Opus 5, devops security, indirect prompt injection, Johann Rehberger, network egress, platform engineering, prompt injection, Python module shadowing, RCE, remote code execution, sandboxing, struct.pyClaude Code’s Auto Mode was bypassed in an attack chain that turned a routine webpage summary into remote code execution, highlighting the limits of AI agent guardrails ...
The Trust Graph: Why Infrastructure Diagrams No Longer Describe Modern Systems
Igboanugo David Ugochukwu | | AI agent security, CI/CD security, GitHub Actions security, IAM governance, identity security, machine identities, non-human identities, OAuth tokens, OIDC federation, platform engineering, reliability engineering, SaaS integrations, secrets sprawl, service accounts, Software Supply Chain, trust amplification, trust bottlenecks, trust cascades, trust graph, workload identityTraditional architecture diagrams miss the identity relationships that now drive breaches and outages. Platform teams need trust graphs that map who and what can act across modern systems ...
4 Security Risks of AI Code Assistants
Zac Amos | | AI (Artificial Intelligence), AI agent security, Code Assistant, generative AI risks, risk managementAI coding assistants can introduce vulnerabilities, privacy risks, and dependency issues. Learn key cybersecurity practices to safely use AI in software development ...
Hush Security Emerges to Eliminate Need for Application Secrets
Mike Vizard | | AI agent security, API key protection, application secrets management, cloud-native security, CNCF SPIFFE, credential theft prevention, credential-free security, DevSecOps secrets management, just-in-time access controls, microservices secrets, runtime identity controls, secrets discovery, secrets sprawl, SPIFFE runtime access, zero trust secretsHush Security today emerged from stealth to provide an alternative approach to protecting application secrets using a platform that is designed to continuously discover them and then apply access controls based on ...
