Three AI coding agents leaked secrets through a single prompt injection. One vendor's system card predicted it

A security researcher, working with colleagues at Johns Hopkins University, opened a GitHub pull request, typed a malicious instruction into the PR title, and watched Anthropic’s Claude Code Securit [...]

Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged

Across the frontier labs, the highest prompt injection figures published this spring are Anthropic’s. Point a red-teamer at its newest model in a browser, and the attacker hijacked it 31.5% of the t [...]

OpenAI admits prompt injection is here to stay as enterprises lag on defenses

It's refreshing when a leading AI company states the obvious. In a detailed post on hardening ChatGPT Atlas against prompt injection, OpenAI acknowledged what security practitioners have known fo [...]

Prompt injection ranks No. 1 with OWASP and No. 12 in the incident record. The attack itself is invisible to a scan.

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 [...]

Prompt injection is exploiting enterprise AI's biggest design flaws by targeting agents, RAG pipelines and model routers

In the past two years, businesses have been trying to fit large language models (LLMs) into support, analytics, development, and internal automation like never before. Along with the increasing adopti [...]

Anthropic published the prompt injection failure rates that enterprise security teams have been asking every vendor for

Run a prompt injection attack against Claude Opus 4.6 in a constrained coding environment, and it fails every time, 0% success rate across 200 attempts, no safeguards needed. Move that same attack to [...]

Red teaming LLMs exposes a harsh truth about the AI security arms race

Unrelenting, persistent attacks on frontier models make them fail, with the patterns of failure varying by model and developer. Red teaming shows that it’s not the sophisticated, complex attacks tha [...]

Microsoft patched a Copilot Studio prompt injection. The data exfiltrated anyway.

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 [...]

The 11 runtime attacks breaking AI security — and how CISOs are stopping them or can stop them

Enterprise security teams are losing ground to AI-enabled attacks — not because defenses are weak, but because the threat model has shifted. As AI agents move into production, attackers are exploiti [...]