Analysis · curated 17 Sep 2026
The AI Help Chat That Gave Away a Password (Prompt Injection)
First reported youtube.com
Coverage timeline
Single-source analysis — first reported, latest, and curated coincide.
Why it matters
Prompt injection remains the top LLM application risk (OWASP LLM01), and this walkthrough clearly illustrates how both direct and indirect injection can hijack an assistant's trusted tool access, reinforcing that filtering banned phrases is not a real defense.
An educational Plaintext video demonstrates prompt injection end-to-end against a shop's AI help chat, showing both a direct attack (a single crafted sentence talks the assistant into revealing a password reset code) and an indirect attack (a malicious instruction embedded in a support ticket that the assistant acts on when asked to summarize tickets). The video frames the fix as scoping tool permissions and treating untrusted text as data that can never authorize an action, referencing OWASP LLM01.