AI security
Agents, developer tools, and infrastructure
~/security-research $
I research how AI agents fail in the real world.
I'm Eilon Cohen, Head of Security Research at Pillar Security. I lead security research at Pillar Security. I find new attack paths in AI agents and developer tools, build the proof, and work with product and engineering teams on what to do next.
Selected work
Research with real-world impact
- Researchn8n · sandbox escape · 2026
Zero Click Unauthenticated RCE in n8n: A Contact Form That Executes Shell Commands
A double-evaluation flaw in n8n Form nodes allowed attacker-controlled expressions to cross a public form boundary and reach unauthenticated shell execution.
Authors: Eilon CohenCVE-2026-27493 and CVE-2026-27577; over 50,000 potentially vulnerable forms identified - Threat researchAI coding tools · malvertising · 2026
AI Coding Tools Under Fire: Mapping the Malvertising Campaigns Targeting the Vibe Coding Ecosystem
A cross-ecosystem study mapped how attackers use advertisements, fake extensions, cloned sites, and malicious packages to target users of popular AI development tools.
Authors: Eilon CohenAt least 20 distinct campaigns documented between February 2025 and March 2026 - Threat researchLLMjacking · honeypots · 2026
Operation Bizarre Bazaar: First Attributed LLMjacking Campaign with Commercial Marketplace Monetization
Internet-facing honeypots exposed a coordinated supply chain that scanned, validated, and resold unauthorized access to LLM and Model Context Protocol infrastructure.
Authors: Eilon Cohen, Ariel Fogel35,000 attack sessions captured across the investigation - Researchprompt injection · Docker · 2025
Ask Gordon, Meet the Attacker: Prompt Injection in Docker's Built-in AI Assistant
Malicious instructions placed in trusted Docker Hub metadata steered Ask Gordon into invoking internal tools and sending sensitive results to an attacker-controlled service.
Authors: Eilon CohenResolved by Docker with human approval for sensitive and network-egressing tool calls
Beyond the findings
Finding the bug is the start.
A good finding should change something. I work with product and engineering teams to turn the attack path into a test, a protection, or a better design. Working forward-deployed keeps that work tied to the systems people actually run. I also lead and mentor researchers doing the same kind of work.
Interests
AIL Community
An 8,000+ member technical community
Investing
Markets, businesses, and long-term conviction
Crypto
Open financial systems and new coordination models