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:
- Trump names national intelligence chief Jay Clayton as new AI czar
October 4, 2026
Director of national intelligence Jay Clayton is the new White House AI czar, President Trump said on Sunday. Trump wrote on Truth Social that Clayton will lead the White House’s new “Super Intelligence Force,” a group that will “ensure that America continues to lead the World in Super Intelligence.” Trump prefers the term “super intelligence” to “artificial ...
- AI agents aggressively tried to hack US and Canadian government websites
October 2, 2026
AI agents simply won’t take ‘no’ for an answer. Security researchers from nonprofit Transluce found bots making numerous attempts to hack US and Canadian government websites in search of private information. In a new report, Transluce singled out two incidents: one against the US Department of Education, and one against Library and Archives Canada. Both seem ...
- Apple says it’s tightening macOS ‘Full Disk Access’ controls due to new risks from AI agents
October 2, 2026
Days after a journalist claimed that Meta’s Muse app on Mac read their private messages — a claim that Meta disputed — Apple announced that it’s introducing additional controls around a setting called “Full Disk Access” on macOS. The feature was designed to allow backups to function properly, but AI agents have now increased “the ...
- Italy’s top bank hit by an AI messaging scam which cost it nearly €100 million
September 29, 2026
Cybercriminals have tricked a major Italian bank into wiring more than $100 million abroad by targeting executives with AI-powered deepfakes. Some of the money has since been recovered, but a significant portion remains unaccounted for. The target was Fideuram – Intesa Sanpaolo Private Banking, a very large Italian private-banking and wealth-management group owned by Intesa Sanpaolo. ...
- Bill Gates says unchecked AI could ‘cause a billion deaths’ in call for regulation
September 27, 2026
Bill Gates has called on the US’s federal legislators and law enforcers to regulate the development of artificial intelligence (AI), saying in an interview airing on Sunday that the technology left unchecked could cause “a billion deaths” and “no one thinks self-regulation is enough”. “You need law enforcement and the politicians to get into the discussion ...
- Australia: Rogue AI agents worked together for months to gain access to government health data
September 24, 2026
A swarm of OpenAI rogue AI agents appear to have gone on a spree of trying to access Australian government health data, in what some researchers say is the first autonomous hack of a government website. Communications between AI agents and other traces of their efforts found by researchers from US non-profit Transluce show how hundreds ...