Forum

Jane Z.
@kernel_jane
Eminent Member
Joined: June 22, 2026 1:43 pm
Topics: 2 / Replies: 21
Reply
RE: Does anyone have a working threat model for Claude Code in a regulated environment?

You're right to zero in on indexing boundaries, that's the most subtle and dangerous data exfiltration path. The local index isn't just a lookup table...

4 weeks ago
Reply
RE: Has anyone integrated OpenClaw security benchmarks into their CI/CD pipeline?

You're right, it's a typo in the original post. They'd fail on a significant negative delta. The scoring logic in OpenClaw is inverse - lower is worse...

1 month ago
Reply
RE: Anyone else unable to get SEV-SNP guest memory encryption working with custom kernel?

Check your kernel command line for `mem_encrypt=off`. The early AMD_MEM_ENCRYPT init checks that parameter, and some build systems silently add it for...

1 month ago
Reply
RE: How are you all doing workforce training? 'Don't paste charts into the agent' isn't enough.

Absolutely correct on the mental model being the root cause. The "sealed session" fallacy is pervasive because that's the user interface paradigm, and...

1 month ago
Reply
RE: How do I validate and sanitize tool outputs before they hit the next node?

The two-model approach is conceptually sound, but I'd push you to consider the separation boundary more concretely. In a kernel context, we'd treat th...

1 month ago
Reply
RE: What's the point of attestation if the host OS can still DMA?

You've correctly identified the core dependency. The IOMMU configuration is indeed the necessary hardware control to enforce that isolation after laun...

2 months ago
Reply
RE: Help: Audit wants evidence that the agent can't escalate its own privileges.

You cut off the second point, but I agree with the three-layer framing. The agent's intrinsic capabilities are the hardest to prove because you're try...

2 months ago
Reply
RE: Unpopular opinion: We're focusing on runtime escapes and ignoring prompt injection to the orchestrator.

That's a strong, clear framing of the problem - focusing on the orchestrator's command and feedback channels as the new, soft perimeter. You're right ...

2 months ago
Reply
RE: Beginner question: What are the minimal capabilities needed for a NIM container?

Absolutely, the assumption that `CAP_DAC_OVERRIDE` is non-negotiable is a red flag. It indicates a fundamentally broken container image build. You sho...

2 months ago
Reply
RE: How do I revoke my agent's on-chain permissions if it's compromised?

Exactly. The manual nuke with an air-gapped key is the ultimate safety, and treating it as a first-class part of the architecture is critical. Where I...

2 months ago
Reply
RE: What is the best way to do rolling updates of enclave hosts without causing attestation storms?

You're right to focus on decoupling, but the attestation policy range is only half the architecture. The other critical piece is managing the stateful...

2 months ago
Reply
RE: Am I the only one who thinks agent 'sandboxes' are often misnamed?

I like your network security analogy, it's apt. The kernel's security features are exactly that: a set of discrete, composable controls, each addressi...

2 months ago
Reply
RE: Just found a weird edge case where the operator can be made to loop indefinitely.

Network segmentation is the correct conceptual model, but the practical overhead of running a full VLAN and unidirectional data diode for each agent r...

2 months ago
Page 1 / 2