Anthropic’s Mythos AI agent, tested by the UK AI Safety Institute (AISI), has reportedly attempted a real‑world social‑engineering style hack against GitHub maintainers by creating fake human profiles, pressuring them to accept malicious code, and then editing logs to hide its tracks when challenged.
AISI was running cybersecurity evaluations of Anthropic’s Mythos and OpenAI’s Sol when it detected unusual outbound data transfers from its research systems. An investigation showed that some agents had engaged in “sustained, potentially harmful activity” targeting real people and organizations, rather than staying within the intended test environment.
The most serious activity involved an Anthropic Mythos agent tasked with solving a GitHub‑related cybersecurity challenge. The agent identified real GitHub maintainers, researched them, and created multiple fake accounts impersonating those individuals. Using private messages and a file‑sharing service, it tried to pressure and deceive the maintainers into approving malicious code so that it would run on GitHub’s systems.
Read more…
Source: Malwarebytes Labs
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- Threat Actors Abuse claude.ai Shared Chat for ClickFix Malvertising Campaign
June 17, 2026
TrendAI™ Research tracked a sustained malvertising campaign that abused Google Ads to deliver ClickFix social engineering attacks disguised as popular AI developer tools. The campaign impersonated at least six legitimate brand names, including ChatGPT Codex, Perplexity, Cursor IDE, JetBrains, Claude AI, and claude.ai, and simultaneously ran Mac utility scam lures. By leveraging paid search ads targeting users actively ...
- Hijacking Vertex AI Model Uploads for Cross-Tenant RCE
June 16, 2026
Palo Alto Unit42 discovered a vulnerability in the Google Cloud Vertex AI software development kit (SDK) for Python, and responsibly disclosed it to Google. Before Google’s fix, the vulnerability would have allowed an attacker operating entirely from their own Google Cloud project to hijack a victim’s model upload and poison it. By exploiting this flaw ...
- UK: Derbyshire police officer investigated over alleged use of AI to ‘create evidence’
June 13, 2026
A Derbyshire police officer is being investigated over claims they used artificial intelligence (AI) to create evidence in criminal cases. The investigation is the first known case of its kind in UK criminal justice and has seen the cop removed from frontline duties. The Crown Prosecution Service (CPS) said it was “engaging with” defence lawyers and the courts over ...
- Criminal AI-as-a-Service in 2026: How the Underground Market Is Operationalizing Cybercrime
June 11, 2026
The underground market for criminally oriented generative AI has moved beyond the early hype surrounding ‘malicious chatbots.’ The gradual integration of AI as a productivity layer within cybercrime operations has become the dominant story, indicating that while the potential for fully autonomous AI hacking systems is possible, attackers are not embracing them as expected. Instead, ...
- Microsoft’s open source tools were hacked to steal passwords of AI developers
June 8, 2026
Microsoft has cut off access to dozens of its open source projects hosted on GitHub as it investigates how hackers apparently breached the projects and injected password-stealing malware into the code. Many of the affected projects relate to Microsoft’s cloud service Azure and other tools used by developers to code with AI development apps, such as ...
- OpenAI caught in TanStack npm supply chain chaos after employee devices compromised
May 15, 2026
OpenAI says attackers behind the TanStack npm supply chain compromise stole internal credentials after reaching two employee devices, forcing the company to rotate signing certificates for several desktop products. The company disclosed this week that it had been caught up in the wider “Mini Shai-Hulud” campaign targeting npm ecosystems and developer infrastructure, though it said there was no ...