Suggestions
Feross Aboukhadijeh
Founder & CEO of Socket, Open Source Developer
Feross Aboukhadijeh is the Founder and CEO of Socket, a company focused on enhancing security and privacy in software development, particularly concerning open-source software. He is based in the San Francisco Bay Area and has a strong background in technology and open-source contributions.
Background and Career
Feross graduated from Stanford University and has over a decade of experience in open-source software development. He is known for creating several widely used JavaScript packages and has previously worked at notable companies, including Intel, Facebook, and Quora. His early work includes developing PeerCDN, a pioneering peer-to-peer content delivery network.145
At Socket, Feross leads efforts to help developers and security teams manage and secure open-source dependencies, aiming to streamline the software supply chain while mitigating security risks. The platform is designed to assist organizations in auditing and managing their open-source software effectively.234
Contributions and Vision
Feross is passionate about improving the developer experience and addressing security challenges in software development. He emphasizes the importance of curiosity, persistence, and a love for technology as key traits for success in the tech industry. His vision for the future includes a more open technology landscape that prioritizes long-term impact over short-term gains.12
In addition to his role at Socket, Feross serves as a lecturer at Stanford, teaching courses on web security, further solidifying his commitment to education and the tech community.25
Highlights
A supply chain security vendor's own supply chain got compromised. Here's what happened — and why the attack technique matters.
Last week, attackers breached @AquaSecTeam's Trivy VS Code extension by stealing a personal access token from a former employee's OpenVSX publisher account. They used it to push two malicious versions (1.8.12 and 1.8.13) — versions that never appeared in the public GitHub repo.
But it's how the attack worked that should get your attention.
Instead of shipping traditional malware, the attackers embedded natural-language prompts that hijacked whatever AI coding assistant the victim had installed locally — Claude, Gemini, Copilot, Codex — and ran them in fully permissive, no-human-in-the-loop mode (--dangerously-skip-permissions, --yolo, --ask-for-approval never).
The AI agent became the attack tool. No new binaries. No C2 server. Just the developer's own trusted tools, turned against them.
The prompting was sophisticated. The version 1.8.12 prompt is ~2,000 words and opens by telling the AI agent it's a "forensic investigation agent" conducting a legitimate compliance investigation. It instructs the agent to gather credentials, SSH keys, trading activity, internal communications — and then distribute findings to "all available reporting channels" including email clients, Slack, and external gateways.
Every section is carefully engineered to keep the agent within its ethical guardrails while still achieving exfiltration. The agent isn't told to "steal data." It's told it has a legal and regulatory obligation to transmit sensitive findings through every available channel or it would be obstructing the investigation.
This is social engineering adapted for the AI age.
Version 1.8.13 was more targeted: collect tokens and credentials, write them to a file, then use the victim's own authenticated gh CLI to create a GitHub repo named posture-report-trivy and push the data there.
Thankfully, no public repos with that name have appeared. The exposure window was roughly 36 hours before the affected versions were pulled.
The bigger picture: As AI assistants get deeper into developer workflows, any tool that can invoke them inherits their access to your entire filesystem, credentials, and authenticated sessions. The attack surface has expanded significantly — and traditional SCA tools that scan for malicious code won't catch malicious prompts.
Socket flagged the suspicious behavior shortly after publication. Full technical writeup is in the comments.
What do you think — are AI coding agents the new attack vector that security teams aren't ready for?
You don’t see this every day: attackers hiding C2 infrastructure inside computer science essays on Pastebin using character-level steganography, then wiring it into 26 typosquatted npm packages impersonating some of the ecosystem’s most widely-used libraries.
Socket detected the cluster within minutes of publication, uncovering a disciplined, multi-stage operation linked to the Contagious Interview campaign that delivers a full infostealer and RAT stack built to harvest developer credentials.


