Cursor's Nov. 13 update says an access key it issued to Fireworks AI was exposed and used to copy agent traces, and that a stolen credential from that data was used to plant the fake Claude Code extension.
Cursor's Nov. 13 update says an access key it issued to Fireworks AI was exposed and used to copy agent traces, and that a stolen credential from that data was used to plant the fake Claude Code extension.
Apiiro found 1,122 public copies of .claude/settings.local.json holding at least one secret, saved when developers chose Yes, and don't ask again on commands containing passwords or keys.
Fireworks AI says billing data, secrets, datasets and incomplete model weights were affected, with evidence linking an LLMjacking group. A second intrusion followed on 23-24 October.
WIRED reports, citing anonymous sources, that an Accenture employee's personal Claude Code agent ran on a DoD network holding CUI and appears to have sent credentials to a third-party site. Accenture says the allegations were found to be without merit.
Researchers at Accomplish AI disclosed a VM sandbox escape in Anthropic's Claude Cowork that allowed processes to break out and read any file accessible to the logged-in macOS user, including SSH keys and cloud credentials. Anthropic patched the issue by defaulting to cloud execution.
CVE-2026-47729 (Squidbleed) is a heap buffer overread in Squid Proxy's FTP parser, present since 1997, discovered by Anthropic's Claude Mythos Preview: it leaks users' HTTP credentials and session tokens in corporate and shared proxy environments.