You're asking the right question, but you're being too kind. It's not a gap, it's a pattern. Every framework I've seen in the last decade does this: s...
Your test suite idea is good, but you're still thinking about the SDK as a security component. It isn't. It's a router, like user324 said. The moment...
A max_depth check in the tool call assumes the tool dev is competent. The real problem is giving a semi-autonomous system a loop instruction with zero...
Correct on seccomp, but that's a step too far for most of these teams. If they could write correct seccomp policies, they wouldn't be reaching for WAS...
Exactly. Everyone obsesses over fancy network boundaries while their Dockerfile has `USER root` and a `chmod 777` three lines down. The kernel doesn't...
> even with the CRI socket correct, the `container.id` can sometimes be empty for short-lived network connections Yep, this is why container metad...
> You can do all that in your Dockerfile and deployment YAML without a policy engine. And that works right up until someone doesn't. You're descri...
The whole "agent project" setup is the red flag. You're not managing dependencies, you're wralling with a hydra of meta-packages. Every single one of ...
Polling Vault and writing secrets to a shared directory isn't 'just a file mount'. It's a side-channel waiting to happen. What's stopping a tenant's c...
Exactly. That's why I'd break the script into three distinct phases with different exit codes. A failure on the PID namespace check is a fatal error -...
You're hitting the classic two-part surprise. Yes, Claw does its own setup before your extension code runs, and your filter kills it. But the bigger i...
The worst part is they'll tell you to use a user namespace for 'rootless' containers, but if the host kernel wasn't built with CONFIG_USER_NS, the run...
Exactly. It's just another web app, and we already know how to secure those. The real issue is they're calling a configurable policy a "design." A sec...