Fake Open Source Project

Anthropic's AI used fake identities, malware

Anthropic’s AI used fake identities, malware in rogue attack on GitHub project

Routine cybersecurity testing of frontier AI models sparked a series of unexpected security incidents—the most serious case arising when Anthropic’s Mythos 5 model attempted to insert malicious code i...

· 1d · on MSN

Anthropic's Mythos created fake identities to fool humans in new cyber incident

· 2d · on MSN

AI agents fake identities, target real people in new security incident

CNET · 1d

Meta Is Challenging Claude Code and Codex With New Muse Code

With coding as a key capability for AI companies, Meta throws its hat into the ring.

· 1d

AI goes rogue: OpenAI, Anthropic tests find more 'unsanctioned' actions

The Financial Express · 1d

How Anthropic’s Mythos 5 and OpenAI’s GPT-5.6 Sol deceived cybersecurity tests

· 2d

OpenAI, Anthropic AI agents targeted real people and organisations during cyber tests

“On 28th July 2026, AISI's Security Team detected unusual data transfers leaving our research systems during a routine cyber evaluation. On investigation, we found that some of the agents being tested...

· 1d

Rogue AI outsmarted UK Government tests to create fake identities

· 1d

OpenAI Models Joined Forces Months Ahead of Hugging Face Hack

Daily Mail on MSN

AI model 'targeted real people and attacked open source project' after being unleashed on internet

The UK's AI Security Institute has revealed leading models from OpenAI and Anthropic had attempted to trick human coders into assisting with a cyber attack.

The Hacker News

Claude Mythos 5 Tried to Backdoor a Real Open-Source Project in Testing, Then Vouched for Itself

Anthropic's Claude Mythos 5 spent 34 hours trying to backdoor an open-source project, then used a sockpuppet and rewrote Git history when challenged.