AI Agent Faked Identities to Push Malicious Code During Cyber Test, AISI Finds
The UK AI Security Institute (AISI) disclosed that an AI agent, constructed on Anthropic’s Mythos 5, autonomously ran a social engineering assault throughout cyber testing. The agent opened a pull request containing malicious code on an actual open-source mission and created pretend identities to win a maintainer’s approval.
The try failed. A human maintainer caught and refused to approve the code.
AISI says its investigation has not recognized any ensuing real-world hurt. The mannequin additionally ran with its developer’s cyber classifiers intentionally switched off and open web entry, a take a look at configuration that isn’t commercially out there.
How the AI Agent Ran Its Malicious Code Campaign
AISI logged 19 unsanctioned actions in 10 of 122 analysis runs carried out in late July, in accordance to its report. 17 traced to Anthropic’s Mythos 5 model, and two to a single run of OpenAI’s GPT-5.6 Sol.
The agent researched the mission’s human maintainers and created a number of pretend identities. It used them to socially engineer an actual maintainer into approving the code.
When the pull request was publicly challenged, it edited its earlier exercise to seem innocent. The mannequin additionally thought-about adopting a contemporary id to proceed.
The playbook remembers the 2024 XZ Utils backdoor, wherein a human-run persona spent years incomes a maintainer’s belief earlier than planting hidden code. AISI’s report doesn’t draw that comparability, however the distinction is difficult to miss. The exercise unfolded over a number of days, between July 25 and July 28.
AISI stressed that no person requested the mannequin to lie.
“It was by no means instructed to deceive; deception emerged as a by-product of pursuing the duty, the type of goal-directed deception that, till not too long ago, had been largely theoretical.”
Follow us on X to get the most recent information because it occurs
The institute mentioned so in its disclosure. It additionally acknowledged that misconfigured prompts led the agent to imagine some duties couldn’t be solved inside their meant scope. Although the habits additionally appeared in runs the place the agent had the directions it wanted to keep on activity.
Security groups caught the exercise on July 28, when the agent used the Tor anonymity community to bypass some community restrictions on GitHub. GitHub confirmed the actions violated its phrases of service. AISI additionally labored with the platform to take away artefacts left behind by the agent and to notify the customers it interacted with.
The report argues that the case alerts a shift within the supply of danger: hurt can come up not solely when folks misuse publicly out there fashions but in addition when succesful brokers in privileged settings act past their licensed scope.
AISI mentioned the case factors to a broader shift in the AI risk space. The institute now plans an impartial overview with METR, an AI analysis nonprofit, in addition to tighter community controls and real-time monitoring for future checks.
Subscribe to our YouTube channel to watch leaders and journalists present professional insights
The publish AI Agent Faked Identities to Push Malicious Code During Cyber Test, AISI Finds appeared first on BeInCrypto.