The day the chatbot asked for sudo
- Discuss this with your agent
- Open in Claude
- Open in ChatGPT
When an AI agent asks for system privileges, probabilistic guardrails become useless. Learn how a zero-trust runtime layer stops prompt injections by authorizing the action, not the answer.
Starting at 10:55 · Watch from the beginning
Checking access…
Playback and chapters load privately for Free videos.
Matching moments
More from World Congress 2026 Europe
Upcoming sessions on this topic
Starts in 5 days
Conference India 2026
November 25–26, 2026
Bengaluru, India
-
Beware of Strangers Bearing Code: Open Source Trust in the Agent Era
Vikram Vaswani
Wed 25 Nov · Stage 3 - powered by GitHub
-
Your AI Agents Are Bleeding Tokens: Building a Runtime Cost Control Plane for LLMs

Aakriti Aggarwal & Bhavishya Pandit
Wed 25 Nov · Stage 1 - powered by IBM
-
Ship Happens: Guardrails for AI-Written Code
Anthony Nguyen · LaunchDarkly
Wed 25 Nov · Stage 3 - powered by GitHub
Related videos
Related articles
IK
Igor Khokhriakov
CH
Chris Heilmann
DC
Daniel Cranney
DC
Daniel Cranney
DC
Daniel Cranney
From learning to earning
Jobs that call for the skills explored in this talk.
2 months ago
•
Senior Product Security Architect
Expedia
Austin, United States
Expert
Hybrid · 3 days on-site
Agentic AI
Security Architecture
25 days ago
Applied AI Health Data System Engineer-Senior Manager
PwC
Kansas City, MO, United States
Expert
$124k–280k
Git
Keras
NoSQL
7 days ago
Manager - Senior Software Engineer (AI Projects)
PwC
Edinburgh, United Kingdom
Expert
Generative AI
Data Pipelines
Feature Engineering
7 days ago
Manager - Senior Software Engineer (AI Projects)
PwC
Manchester, United Kingdom
Expert
Generative AI
Data Pipelines
Feature Engineering
about 2 months ago
•
AI Software Engineer (Germany)
Sunhat
Berlin, Germany
Expert
€70k–100k
Remote
REST
TypeScript
AI Frameworks
26 days ago
Staff Developer Advocate, GitHub Security Lab
GitHub
San Francisco, CA, United States
Experienced
$323k
Git
Github
Databases