Research · curated 24 Sep 2026
Jev Is Not a Language Model, but It Breaks Like One: Prompt Injection Against a Typed Decision Model
First reported checkpoint.com
Coverage timeline
Single-source research — first reported, latest, and curated coincide.
Why it matters
Jev-style typed decision models get wired directly into systems that act on their verdicts with no human-readable text to review, so the finding that they inherit the same prompt-injection weaknesses as chatbots means externally-controlled data can silently flip automated hiring, insurance, or investment decisions.
Check Point researchers tested prompt injection against Jev, a new 'typed decision model' from TypeSafe AI that returns structured verdicts (choices, yes/no, scores with probabilities) instead of text for machines to consume rather than humans to read. Placing it in a realistic investment-risk application and injecting adversarial content into the judged document, they found every configuration breakable — risk downgraded to low and investment advised on a document full of warning signs — at roughly 50 cents per successful break, with structured input and distrust instructions providing little protection and reasoning being the strongest measured defense.