TechThe Register1h ago

AI agent suggested installing a malware package. Engineer almost took

AI agent suggested installing a malware package. Engineer almost took its advice

AI agent suggested installing a malware package. Engineer almost took

TL;DRAI suggested installing malicious code; human review caught it in time.

Why it matters: AI tools can't be trusted alone for security decisions; human oversight remains critical.

Fortunately, the company had a policy of checking source code on GitHub first

Read full article

Source: The Register · Opens in new tab