CVEs, exploits, and security flaws in AI frameworks, models, and infrastructure.
A vulnerability in Discourse's AI content triage feature lets a malicious user craft a post that prompt-injects the LLM into returning JavaScript, which is then rendered unescaped in the admin review queue. Patch available.
Novee Security disclosed Cordyceps, a class of GitHub Actions vulnerabilities exploitable by any free GitHub account. AI coding agents are amplifying the problem by reproducing the same insecure patterns at scale.
Zafran Security disclosed four authorization vulnerabilities in Dify, the AI platform powering over one million applications, that allow cross-tenant AI conversation exfiltration — some without any authentication beyond a free account.
Johann Rehberger's DEF CON Singapore research demonstrates how indirect prompt injection chains into Microsoft Copilot's memory feature to plant a persistent backdoor — one that survives across every future session, not just the compromised one.
CVE-2026-47729 (Squidbleed) is a heap buffer overread in Squid Proxy's FTP parser, present since 1997, discovered by Anthropic's Claude Mythos Preview: it leaks users' HTTP credentials and session tokens in corporate and shared proxy environments.