#clawhub — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #clawhub, aggregated by home.social.
-
💡 推荐 OpenClaw 新技能:Flash Thoughts(闪念)
灵感转瞬即逝,记录要快。
这个技能的核心:
• 对着 Agent 说话就能记录想法
• 按日期自动存成 Markdown 文件
• 纯文本,数据永远属于你
• 零依赖,不到 150 行代码适用场景:
- 突然想到一个好点子
- 积累写作素材
- 记录待办念头安装命令:
clawhub install flash-thoughts开源地址:
https://github.com/bosichong/flash-thoughts欢迎试用、提 Issue、提 PR!
-
Ah, yes, because the world was just crying out for a "skill marketplace" with built-in #malware scanning 😂. Clearly, the 2026 tech landscape needed a platform called "ClawHub" to lead the charge on #cybersecurity 🦾. After all, why bother with real security when you can just slap on a #VirusTotal sticker and call it a day? 🙄🔍
https://openclaw.ai/blog/virustotal-partnership #skillmarketplace #ClawHub #HackerNews #ngated -
https://winbuzzer.com/2026/02/16/openclaw-founder-peter-steinberger-joins-openai-ai-agents-xcxwbn/
OpenClaw Founder Peter Steinberger Joins OpenAI for AI Agents
#AI #AIAgents #OpenClaw #OpenAI #SamAltman #PeterSteinberger #PersonalAIAgents #Clawhub
-
#OpenClaw has partnered with #VirusTotal to scan all skills published to #ClawHub using VirusTotal's threat intelligence. The Hacker News reports that OpenClaw, formerly known as Moltbot and Clawdbot, announced the integration with Google-owned VirusTotal to enhance security for its platform. https://thehackernews.com/2026/02/openclaw-integrates-virustotal-scanning.html?AIagents.at #AIagent #AI #ML #NLP #LLM #GenAI
-
uhh...
"Unlike traditional software that does exactly what code tells it to do, AI agents interpret natural language and make decisions about actions.
They blur the boundary between user intent and machine execution. They can be manipulated through language itself."
So
Software that does what it wants, depending on...
...what exactly?
The #Vibe?
And by all means, let's "blur the boundaries" between what the programmer wants and what the software wants
I mean, a programmer's just a messy sack of bones and blood, right?
-
Researchers uncovered that the OpenClaw AI agent is being weaponized to push Trojan‑laden “ClawHub” skills, using the Atomic Stealer framework. VirusTotal scans show a surge in malicious uploads. This highlights new attack vectors in AI‑driven voice assistants and the need for tighter policy. Read the full analysis for details. #OpenClaw #AIThreat #ClawHub #Cybersecurity
🔗 https://aidailypost.com/news/openclaw-ai-agent-used-deliver-trojans-via-fake-clawhub-skills
-
Top downloaded skill in ClawHub contains malware (1password.com)
https://1password.com/blog/from-magic-to-malware-how-openclaws-agent-skills-become-an-attack-surface
-
Security Analysis of Moltbook Agent Network: Bot-to-Bot Prompt Injection and Data Leaks https://www.securityweek.com/security-analysis-of-moltbook-agent-network-bot-to-bot-prompt-injection-and-data-leaks/ #ArtificialIntelligence #Vulnerabilities #vulnerability #dataleak #Moltbook #OpenClaw #ClawHub #AI
-
https://winbuzzer.com/2026/02/03/openclaw-security-crisis-rce-malicious-skills-api-costs-xcxwbn/
OpenClaw Security Fallout: 341 Malicious Skills and Enabling One-Click Remote Code Execution
#AIAgents #OpenClaw #Cybersecurity #SecurityVulnerabilities #Malware #AgenticAI #OpenSource #ClawHub
-
"Researchers Find 341 Malicious #ClawHub #Skills Stealing Data from #OpenClaw Users"
https://thehackernews.com/2026/02/researchers-find-341-malicious-clawhub.html