You can replace Anthropic’s message plugins for sth more capable.
@steipete
-
Software Evolution: New AI Vectors Emerge Continuously
By
–
Software is never done. New vectors emerge as we learn.
-
Securing AI Agents: Sandboxing and Credential Management Strategies
By
–
Yes, you can enable sandboxing and decide what your agent has access too. We also have secure storage for credentials; there’s also plugins who swap these at the proxy level – depending what level of isolation you prefer. You can also fully swap to local models.
-
TrustClaw faces FUD and mudslinging from competing companies
By
–
By now it’s mostly a problem with FUD and too many companies that try to sell TrustClaw versions by putting us into mud.
-
AI Security Framework: Sandbox, Allow-lists, Access Control
By
–
That was the case in December. 4 months and thousands of work hours later, we have a great security concept; you can go all yolo, use a sandbox (Docker or OpenShell), there are allow-lists and per-access exec allow/deny prompts. There’s hundreds of security researchers that
-
Selective GPT API Dialog Access: Understanding Availability Differences
By
–
Oh see, I did not know that, never encountered these dialogs in my GPT API access long before I started. Is that selective then?
-
GPT 5.4-Cyber Reverse Engineering Security Threats Response
By
–
If you look at GPT 5.4-Cyber and it's ability for closed source reverse engineering, I have bad news for you.
— Peter Steinberger 🦞 (@steipete) 15 avril 2026
I do very much feel the pain though, there's hundreds of teams that try to poke holes into @openclaw. Our response has been of rapid iteration and code hardening. Which… https://t.co/duLmTxlfuqIf you look at GPT 5.4-Cyber and it's ability for closed source reverse engineering, I have bad news for you. I do very much feel the pain though, there's hundreds of teams that try to poke holes into @openclaw
. Our response has been of rapid iteration and code hardening. Which -
QA Lab vulnerability reports and code management practices
By
–
@buddyhadry Sending vulnerability reports for the QA Lab code we aren't shipping in prod at all? Come on. Send a PR instead if this is relevant for your setup.