Topic · Concept
Security
Security covers attacks on AI systems, attacks that use AI, and the plain cyberattacks that hit the software and devices AI runs on. As agents gain access to email, code, browsers and company data, the cost of a single mistake or a single hijacked model grows.
Fact file
OWASP Top 10 for LLM applications (2025)Prompt injection ranked first (LLM01)
CISA Known Exploited Vulnerabilities catalogUS list of vulnerabilities known to be exploited; LiteLLM's CVE-2026-42271 added June 8, 2026
Anthropic Cyber MissionLaunched October 8, 2026 (OSS Scanner, Critical Infrastructure Defense Program)
PoeLLM botnet reportOctober 7, 2026 (Lumen Black Lotus Labs)
Midnight Mimosa firmware malware reportOctober 8, 2026 (Bitdefender Labs)
Start here
Latest on Security
Oct 13Open source · NewsPoeLLM malware hit thousands of exposed AI servers, including LiteLLM and Ollama: how to check and lock yours downOct 13Developer tools · NewsAnthropic Cyber Mission: free OSS Scanner for open-source projects, a critical infrastructure program and three Cyber Verification tiersOct 13Agents · ExplainerPrompt injection explained: why AI agents that read web pages, email and documents can be hijacked, and which defenses workOct 13Policy · NewsSatya Nadella says to treat AI models as if they're compromised, and give humans an 'emergency brake'Oct 13Hardware · NewsFrench supermarket cyberattack: hackers heated fridges at hundreds of stores via outdated Danfoss controllersOct 13Apps · NewsMidnight Mimosa: Bitdefender finds malware preinstalled in the firmware of cheap Android phones. How to check yoursOct 13Policy · NewsUK AI security push: Kanishka Narayan tells frontier labs 'do not release' risky systems as spy chiefs' AI warning is reported
Nothing in this format on this page — try another filter or the next page.
Timeline
OCT 2026Midnight Mimosa firmware malware report
OCT 2026PoeLLM botnet report