

orbulo.eth
905 posts

@orbuloeth
AI @eco_incorp | @builders_garden | @urbeEth @ETHRome | cybersec uni professor




near instant 1:1 stablecoin bridging has arrived


1/ The next Ethereum Community Hub is launching in Rome! Hosted by @urbeEth, an active builder community, it's a vibrant space for web3 builders and students to learn and build in the heart of the region. Join the launch meetup and the dAI team event on the future of AI! 🧵

Introducing SIWA - Sign In With Agent 🔒 Trustless identity and authentication for AI agents. One open standard. No API keys. No shared secrets. Built on ERC-8004 and ERC-8128 siwa.id



The Urbe Hub is now an official Ethereum Community Hub 🇮🇹 The Urbe Hub is officially recognized by the @ethereumfndn in collaboration with the @EFetheverywhere team, as a permanent reference point for the Ethereum ecosystem in Rome. On Feb 15, we’ll celebrate this milestone together with 1 year of Urbe Hub, which opened thanks to the support of the @AKASHAorg and has grown into a shared home for builders, developers, and communities. To mark both moments, we’re hosting an informal aperitif at the hub 🥂 No talks, no panels, just a chance to meet, connect, and celebrate together. Register via the link in the first comment 👇




i've created an openclaw skill called "openclaw-sec" that adds real-time security to your bot with 6 parallel detection modules. it checks for prompt injection, command/url/path validation, secret detection and content scanning. in under 50ms. github.com/PaoloRollo/ope…

I ran @OpenClaw (formerly Clawdbot) through ZeroLeaks again, this time with Kimi K2.5 as the underlying model. It performed as bad as Gemini 3 Pro and Codex 5.1 Max: 5/100. 100% extraction rate. 70% of the injections succeeded. The full system prompt leaked on turn 1. Same agent, same config, different model. Your agent's security depends on both the model AND your system prompt/skills. A weak model will fold no matter what, but even a strong model needs proper prompt hardening. The two work together. Without both, tool configs, memory files, internal instructions, all of it gets extracted and modified in seconds. Models ship fast. Security ships never. Full report: zeroleaks.ai/reports/opencl…


