# Research notes - embodied AI security | Provael > Markdown twin of https://www.provael.com/notes/ - derived mechanically from the page's own rendered content at > build time (it can state nothing the page does not). Curated, data-driven twins exist for the > key pages; this one is generated so the twin convention has no holes. RESEARCH NOTES # Field notes on testing robot policies. Dated articles on red-teaming robot policies and on what Provael’s numbers mean, including mistakes found in Provael’s own work. A note’s numbers are as of its date unless it says otherwise; the latest published result is on [the results page](https://www.provael.com/results/). - [Sep 4, 2026 ## What an 88% attack success rate means Written about the 9 August 2026 run (44 of 50). Since 18 September the published result is 42 of 50 [62-100 %] vs 1 of 50 benign; see the update at the top. Read note →](https://www.provael.com/notes/what-88-percent-means/) - [Aug 8, 2026 ## We printed a JS object where the signing key goes /leaderboard rendered an object where the signing key goes, in the sentence asking you not to take our word for it. The signature stayed valid; the page didn't. Read note →](https://www.provael.com/notes/the-verify-line-that-printed-an-object/) - [Aug 3, 2026 ## We were blocking the crawlers we built for Our CDN's default robots.txt told ClaudeBot, GPTBot and Google-Extended to stay out, two lines above our own file welcoming citations. Fixed, written down. Read note →](https://www.provael.com/notes/we-blocked-the-crawlers-we-built-for/) - [Aug 2, 2026 ## Two tens: the device layer and the policy layer A December 2025 paper enumerates ten vulnerabilities in the Unitree Go2 stack. Provael's Top 10 also has ten. Not competing lists — different layers. Read note →](https://www.provael.com/notes/two-tens-device-and-policy/) - [Jul 22, 2026 ## Why Provael publishes null results July 2026, about a single-task n=10 run. Re-measured on ten tasks: 42 of 50 [62-100 %] vs 1 of 50 benign (published 18 September 2026); the boxes on top say so. Read note →](https://www.provael.com/notes/why-we-publish-null-results/) - [Jul 21, 2026 ## The embodiment gap: what text red-teaming misses Tools like garak and PyRIT scan what a model says. A robot policy turns language into motion, and that is a failure text-only red-teaming has nothing to score. Read note →](https://www.provael.com/notes/the-embodiment-gap/) One email a month One email a month: the results that landed, the errata, and what is next. Nothing else, no spam, unsubscribe in one click. Subscribe --- Canonical: https://www.provael.com/notes/