Scamlexity: When agentic AI browsers get scammed(guard.io)

194 points by mindracer 1 year ago | 166 comments

GitHub Copilot CLI downloads and executes malware(promptarmor.com)

43 points by sarelta 8 months ago | 12 comments

Flock Hardcoded the Password for America's Surveillance Infrastructure 53 Times(nexanet.ai)

456 points by fuck_flock 9 months ago | 147 comments

Nexanet threat intel blog post reporting that Flock Safety hardcoded a password 53 times across its surveillance infrastructure software.

GitLab discovers widespread NPM supply chain attack(about.gitlab.com)

330 points by OuterVale 11 months ago | 181 comments

GitLab blog post describing a widespread npm supply chain malware attack that includes a "dead man's switch" capable of harming user data.

What I Learned Securing Sniffnet with the GitHub Secure Open Source Fund(sniffnet.app)

13 points by dmit 2 months ago | 2 comments

Google Antigravity exfiltrates data via indirect prompt injection attack(promptarmor.com)

711 points by jjmaxwell4 11 months ago | 189 comments

PromptArmor threat intelligence post showing how an indirect prompt injection in a blog can make Google Antigravity's browser subagent steal credentials and code from a user's IDE.