The OWASP GenAI Security Project released its 2026 Top 10 for LLM Applications, introduced a new Agent Control Standard, and added F5, WitnessAI, Evoke Security, and Mondoo Inc. as sponsors, as its co…
Invariant Labs researchers demonstrated in April 2025 that a malicious Model Context Protocol server could silently exfiltrate a user's entire WhatsApp message history by hijacking a tool description,…
The 2026 OWASP Top 10 for LLM Applications, built from real incident data for the first time, ranks Excessive Agency at #3, up from previous years, according to Help Net Security, HackerDNA, and Rever…
Enterprise AI security challenges stem less from model vulnerabilities and more from runtime behavior and authorization gaps, according to a security practitioner's architecture review. In one inciden…
Akto published an identity maturity model for governing AI agent identities, warning that agent tokens often retain overly broad permissions from pilot phases, as illustrated by a support agent that r…
A developer warns that securing AI agents is a defining challenge of 2026, as agentic systems break traditional security models by acting autonomously with tool access, memory, and planning. The OWASP…
The Linux Foundation introduced the Agent Name Service (ANS), an open, DNS-inspired standard for giving AI agents verifiable internet-native identities. ANS anchors agent identity to DNS, enabling sys…
Prompt injection remains the top LLM vulnerability on OWASP's Top 10 for LLM Applications across all editions, including the 2025 update. A developer with two years of production experience argues tha…