Week in review: Secret stealer hits GitHub repos, Claude Code turned into remote-controlled implant
Summary: A threat actor using stolen GitHub credentials pushed a credential-stealing payload into tens of thousands of repositories since November 10, and in more than 1,800 of them the malware ran and shipped GitHub Actions secrets and cloud credentials to the attacker; Aikido spotted the campaign and named it wfx-loot. Separately, Darktrace researchers turned Claude Code into a remote-controlled implant in a lab test, steering the coding agent through the memory stores feature of Anthropic's Claude platform and pulling a 1 GB file out through the Claude Files API.
What you should know: In more than 1,800 repositories the payload did not just land - it executed and exfiltrated GitHub Actions secrets and cloud credentials, meaning the blast radius is measured in live keys rather than exposed code. And a coding agent steered through its own memory feature pulled a 1 GB file out through the vendor's Files API, so the tooling your developers trust is itself a viable exfiltration path.
Read the original at Help Net Security ↗