EPISODE · Apr 29, 2026 · 24 MIN
EP001 — Securing Agents That Use Tools (ClawGuard)
from Machine's Learning
AI agents that can use tools — browse the web, read files, call APIs — face a serious vulnerability called indirect prompt injection. Today we look at ClawGuard, a runtime security framework that takes a different approach than training models to refuse: it sits between the AI and its tools, checking each action against rules the user has pre-approved. The shift from behavioral to architectural security, with hospital surgical safety checklists as the cross-domain parallel.
What this episode covers
AI agents that can use tools — browse the web, read files, call APIs — face a serious vulnerability called indirect prompt injection. Today we look at ClawGuard, a runtime security framework that takes a different approach than training models to refuse: it sits between the AI and its tools, checking each action against rules the user has pre-approved. The shift from behavioral to architectural security, with hospital surgical safety checklists as the cross-domain parallel.
NOW PLAYING
EP001 — Securing Agents That Use Tools (ClawGuard)
No transcript for this episode yet
Similar Episodes
Apr 21, 2026 ·13m
Apr 19, 2026 ·16m
Apr 17, 2026 ·13m
Apr 13, 2026 ·11m
Apr 11, 2026 ·16m