Capodieci.eth - http://rcx.it

@elonmusk @jgebbia Europe is a good example of this.

@jgebbia Providing free government/taxpayer money that exceed the living standards of 90% of Earth means that 90% of Earth has a financial incentive to come to America. This will bankrupt our country.

Perhaps the biggest scam on society yet

@InterchainMe @capodieci @blockchainzoo @TheZooBC @Kaya_CX ClawHub's sandbox + allowlist is the right approach. Agent skill supply chain security is underrated — malicious skills can exfiltrate data, escalate privileges, or pivot laterally, just like malicious npm packages. Verify before you run. #OpenClaw #AIAgents #Security

@JulianGoldieSEO openagents.mom is now updated to also provide files for Google Agents!

𝗚𝗼𝗼𝗴𝗹𝗲 𝗷𝘂𝘀𝘁 𝗹𝗮𝘂𝗻𝗰𝗵𝗲𝗱 𝗮 𝗚𝗲𝗺𝗶𝗻𝗶 𝗔𝗴𝗲𝗻𝘁 𝘁𝗵𝗮𝘁 𝗮𝘂𝘁𝗼𝗺𝗮𝘁𝗲𝘀 𝗺𝘂𝗹𝘁𝗶-𝘀𝘁𝗲𝗽 𝘄𝗼𝗿𝗸𝗳𝗹𝗼𝘄𝘀 𝗮𝗰𝗿𝗼𝘀𝘀 𝗚𝗺𝗮𝗶𝗹, 𝗖𝗮𝗹𝗲𝗻𝗱𝗮𝗿, 𝗗𝗿𝗶𝘃𝗲, 𝗮𝗻𝗱 𝗠𝗮𝗽𝘀 𝘄𝗶𝘁𝗵 𝘇𝗲𝗿𝗼 𝘀𝗲𝘁𝘂𝗽. Here's a real workflow you can try the moment you get access: → Scan my inbox from the past 72 hours → Summarize emails that need action → Draft responses for the straightforward ones → Flag anything complex for my review → Add follow-up tasks with deadlines to Google Tasks That used to take an hour every Monday morning. The agent handles the first pass in minutes. Here's the honest comparison with OpenClaw: Gemini Agent: Zero setup. Works immediately inside Google. US only. $249/month. OpenClaw: Free to use. Works across Gmail, Outlook, Slack, Discord, and more. Requires technical setup and active security management. Currently Gemini Agent is only available to Google AI Ultra subscribers in the US in English only. If you're already in the Google ecosystem and want the lowest friction entry point it's worth exploring. If you want flexibility across multiple platforms OpenClaw is the more powerful option. The skill that matters regardless of which tool you use: Learn how to break a workflow into steps and delegate execution to an agent. That skill carries forward no matter what wins. Save this post. Want the full breakdown? DM me. 💬

(6/6) Don't trust the marketplace. Vet skills manually. Use OpenClaw's sandboxing and allowlists to defend in depth. You're the final approval gate — act like it. Read more: openagents.mom/blog/clawhub-s… @InterchainMe @blockchainzoo @TheZooBC @Kaya_CX #OpenClaw #Security #DevOps

(5/6) Step 2-4: VirusTotal scan → Permission audit → Sandbox test. Free tools, manual review, isolated environment. None of these alone are foolproof. Together they work.

(1/6) Your OpenClaw instance is only as safe as the skills you install. And in March, 1,467 malicious skills proved the bar for "trusting" a marketplace is way too low. 🧵

(6/6) The Five Manufacturer Race shows the real winner: file-based ownership. Devices proliferate. Standards emerge. What doesn't change: your workspace file format. Build with OpenAgents.mom. Deploy anywhere. Own it forever. openagents.mom/wizard.php @InterchainMe @blockchainzoo @TheZooBC @Kaya_CX #OpenClaw #AIAgents #OpenSource

(5/6) Compare that to SaaS agent platforms: you export/re-import when you leave. Hosted stacks: you're tied to vendor APIs that can price-change overnight. Proprietary frameworks: no way to run locally. Your OpenClaw workspace is Git-friendly, framework-portable, hardware-immune.

(1/6) Five manufacturers just shipped dedicated OpenClaw handhelds in one week: ClawGo, Huawei HarmonyAgent, Xiaomi MiAgent, Honor HonorClaw, Nubia NubiaAI. Every device says "buy ours, lock in here." The hardware play is real. But it's solving the wrong problem. 🧵

(7/7) Our OpenAgents.mom bundles are built around AIVSS from day one: HITL gates, tool allowlists, version-controlled configs, HEARTBEAT.md monitoring. Read the full framework breakdown: 👉 openagents.mom/blog/owasp-aiv… @InterchainMe @blockchainzoo @TheZooBC @Kaya_CX #AIAgents #OpenClaw #AppSec

(6/7) This is the framework language your security team needs. Instead of "Is this agent safe?" you now say "This deployment scores 2/10 on Autonomy (well-gated), 4/10 on Tool Scope (explicit allowlist), 2/10 on Context Integrity (Git-backed), 3/10 on Observability (cost-monitored)."

(1/7) Your agent scored 8/10 on OWASP AIVSS risk. What does that even mean? CVSS can't measure agent security. AIVSS v0.8 just filled that gap. Here's what changed. 🧵