درباره این اپیزود
What does it mean to build securely when agents can negotiate their own guardrails? And what happens to the web — CLIs, frameworks, even the browser itself — when the primary user is no longer human? At AI Native DevCon London, Simon Maple sat down with two panels of experts to find out.
First: a security roundtable with Joseph Katsioloudes from GitHub, Liran Tal from Snyk, and John Groetzinger from Cisco.
Then: a web AI conversation with Dana Lawson from Netlify, Maximiliano Firtman from codemia, and James Moss from Tessl.
What we cover:
– Why 83% of enterprises plan to deploy AI but only 29% feel ready to do so securely
– Prompt injection as a risk you have to accept — and how least privilege and sandboxing are your real defences
– The "agent experience" concept: why systems built for human eyes fail at machine scale
– Whether fundamentals like HTTP, semantic HTML, and accessibility still matter when agents do the heavy lifting
– How WebMCP lets websites expose tools directly to agents
— and why blocking them is like trying to turn off the sun
در این اپیزود
یادداشت ها را نشان دهید 🔗
رونوشت 🔗
00:00:00.400 --> 00:00:02.640
I think it's really an unsolved problem, largely, you know.
00:00:02.799 --> 00:00:07.440
Because a lot of times people have way too much confidence in the agent and they get very lazy, and that's what concerns me the most.
00:00:07.679 --> 00:00:18.079
Imagine a skill or something that does an action uh but then to fetch more information to fulfill that, they get that from like an authoritative source, which could have been prompt injected.
00:00:18.160 --> …