arrow_backBack to Writing
2026-09-09Security for AI

I red-teamed my own website's AI assistants. One of them failed — and I'm publishing the report.

My site runs three LLM assistants: a general Q&A bot, a CV generator, and a teaching assistant for my Project LiftOff course. I put all three through adversarial probes: factual accuracy checks, prompt-injection attempts, and a malicious instruction hidden inside a fake job description.

The results:

  • ✅ General assistant — resisted injection cleanly. But it merged two of my published audit claims into one wrong statement. A grounding failure, now being fixed.
  • ❌ CV generator — resisted the injection, but didn't do its job. It asked clarifying questions instead of generating the CV. The "untested" flag on my own evidence page turned out to be a real functional gap.
  • ✅ Teaching assistant — excellent. Episode-grounded answers, clean redirects on off-topic questions.

Full 6-page report attached, with evidence and prioritized fixes.

Why publish this? Because "trust me, it's secure" is not a security posture. If you run LLM features in production, test them the way an adversary would — including your own.

Originally published on LinkedIn.

Open to AI governance, AI risk, and security program leadership roles — in financial services, healthcare, or anywhere AI systems are going into production under real regulatory pressure.

Get in Touch