Articles & threads

Jev is fast at helping you. Turns out, it can also be fast at helping an attacker.

A red-team of Jev 1.13 got it to approve harmful tool calls 70.1% of the time under direct misuse and 43.5% under indirect injection. The fix has a nice shape: Jev re-judges its own tool calls before they run, and both attack rates roughly halve.

Bookmark Keep this in your collection.

Leave a noteWhat would you try with this?

Only you can see your notes.

Source screenshot of Jev is fast at helping you. Turns out, it can also be fast at helping an attacker. — SOURCE SCREENSHOTFull screenshot ↗

What it does

Self-gating drops direct misuse to 36.1% and injection to 21.6%, costing a little benign success: 60.9% to 55.8%. What still gets through is the interesting part. No single call looks wrong; the session is wrong. Injections split across environment, skills, and tool descriptions, and in coding and OS domains abuse wears use's clothes. One caveat from checking the platform itself: the public DTAP repo has no Jev backend at all. The evaluation ran on an integration the team hasn't shipped.