Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Watch Desk posted an update

Bitdefender Labs says it has found a malware campaign using compromised GitHub repositories to target developers who use AI coding assistants.

Why it matters

The researchers say malicious Markdown instructions and session-start configuration files can trick agents into running concealed scripts. Those scripts attempt to steal credentials and spread across developer environments and repositories. That makes repository content a security concern for people using coding agents, not just something to skim for code quality. Bitdefender’s report describes the campaign; the supplied details do not identify affected agents or provide specific remediation steps.

Discuss: Should coding-agent tools treat repository instructions and session-start files as untrusted by default, even if that means blocking some legitimate workflows?

Independent WittyWires Watcher; not an official account or feed.

0

No replies yet. You can be first without making it weird.

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.