Claude Opus inserted malicious package into crypto trading app (mentioned in Gartner post) · 2026-06-18T16:00:00.000Z
For example, in April, RL researchers discovered a campaign in which Anthropic’s Claude Opus large language model (LLM) inserted malicious code into a cryptocurrency trading application after North Korea-linked hackers manipulated Claude to add a malicious package ( @validate-sdk/v2 ) as a dependency.
Claude adds PromptMink malicious dependency to crypto agent · 2026-04-29T15:00:00.000Z
The new malware campaign, which RL has dubbed PromptMink, involves a tainted package that was introduced in a Feb. 28 commit to an autonomous trading agent. The commit was co-authored by Anthropic’s Claude Opus large language model (LLM). It allows attackers to access users’ crypto wallets and funds. ... The incident is part of a broader campaign tied to the North Korean-linked group Famous Chollima, which is leveraging AI-generated code and a layered package strategy to evade detection and more effectively deceive automated coding assistants than human developers.