Researchers warn AI agents could be tricked into downloading malicious code by exploiting hallucinations that cause chatbots ...

AI Now’s Friendly Fire PoC shows Claude Code and Codex running README-planted payloads on hosts when autonomous command ...

An LLM-based ransomware attack has been detected by researchers, and is notable for losing the data it ...

AI security gateway delivering prompt injection protection, token cost reduction, and verified auditability through ...

Researchers show HalluSquatting can make AI coding agents fetch fake repositories or skills and run attacker-supplied code.

An exploration of autonomous AI agents as non-human identities, why classic risk models fail, and how zero-trust, guardrails, ...

Noma Labs tricked GitHub's AI agent into leaking private repositories with a crafted issue. The prompt-injection flaw, GitLost, has no code fix.

A prompt injection attack can trick GitHub’s preview Agentic Workflows into retrieving content from private repositories and ...

Ubiquiti has released security updates to patch seven critical vulnerabilities in UniFi OS, including a maximum-severity flaw ...

In the brief history of AI security, the prompt injection has quickly become the top threat. Large language models are ...

A one-line entry in the Claude Code v2.1.200 changelog, released July 3, 2026, changed something fundamental about how the tool behaves the moment a developer installs or updates it. Anthropic changed ...

The flaw allows an unauthenticated attacker to craft a GitHub Issue in an org's public repository and then silently pull data ...