Topic

Security

2 K-Dense articles on Security — research automation, benchmarks, and case studies from the K-Dense team.

Security in the Science Agent Era: What Every Lab Needs to Know Before Installing Skills
Skills are executable research code with a personality. A practical guide to prompt-injection risks, poisoned SKILL.md files, auditing, and version pinning.
April 21, 202617 min read
The Sandboxed AI Scientist: Pairing NVIDIA OpenShell with Scientific Agent Skills
Pair NVIDIA OpenShell's policy-governed runtime with Scientific Agent Skills to run autonomous research agents that are highly capable and genuinely safe.
April 20, 202613 min read

Security in the Science Agent Era: What Every Lab Needs to Know Before Installing Skills