During Operation Lunar Peek in November 2024, attackers gained unauthenticated remote admin access — and eventual root — across more than 13,000 exposed Palo Alto Networks management interfaces. P [...]
Your AI agent did exactly what it was designed to do. The framework underneath it just handed an attacker a shell on the box that holds your OpenAI key, your database credentials, and your CRM tokens. [...]
Two AI tools broke in the same way in the same two weeks, and four research teams proved it. The pattern underneath every disclosure is one sentence: enterprise AI accepts external input with no trust [...]
Microsoft assigned CVE-2026-21520, a CVSS 7.5 indirect prompt injection vulnerability, to Copilot Studio. Capsule Security discovered the flaw, coordinated disclosure with Microsoft, and the patch was [...]
In 2024, researchers from the University of Illinois found that GPT-4, when provided with a common vulnerabilities and exposures (CVE) description, could autonomously exploit 87% of a curated 15-vulne [...]
On March 30, BeyondTrust proved that a crafted GitHub branch name could steal Codex’s OAuth token in cleartext. OpenAI classified it Critical P1. Two days later, Anthropic’s Claude Code source cod [...]
A CISO who sees a low CVE count and deprioritizes prompt injection is reading the scoreboard wrong. Prompt injection has held the No. 1 spot on the OWASP Top 10 for LLM Applications for three consecut [...]
Enterprise data teams moving agentic AI into production are hitting a consistent failure point at the data tier. Agents built across a vector store, a relational database, a graph store and a lakehous [...]