Secure Trajectories by Sondera
Subscribe
Sign in
Home
Sondera
Archive
About
Hooking Coding Agents with the Cedar Policy Language
A reference monitor built on the trajectory event model.
READ THE LATEST
Most Popular
View all
How We Hijacked a Claude Skill with an Invisible Sentence
Oct 20, 2025
•
Josh Devon
33
10
5
Your AI Agent Just Got Pwned
Dec 8, 2025
•
Matt Maisel
30
2
6
We Told OpenClaw to rm -rf and It Failed Successfully
Feb 4
•
Josh Devon
17
2
5
Building More Reliable Agents with the OWASP Top 10 for Agentic Applications
Dec 19, 2025
•
Josh Devon
16
3
Latest
Top
Discussions
Claude Code's Plan Mode Isn't Read-Only, But You Can Fix It
Making "read-only" a rule instead of a suggestion.
Mar 2
•
John Brock
5
2
We Told OpenClaw to rm -rf and It Failed Successfully
Policy as code guardrails for AI agents
Feb 4
•
Josh Devon
17
2
5
Gas Town Needs a Citadel
Why Industrialized Agent Orchestration Requires Industrialized Control
Jan 21
•
Josh Devon
4
6
3
Supervising Ralph: Why Every Wiggum Loop Needs a Principal Skinner
From Naive Persistence to Reliability
Jan 13
•
Josh Devon
8
1
4
Building More Reliable Agents with the OWASP Top 10 for Agentic Applications
How to use the new security standard as your reliability roadmap.
Dec 19, 2025
•
Josh Devon
16
3
Your AI Agent Just Got Pwned
A Security Engineer's Guide to Building Trustworthy Autonomous Systems
Dec 8, 2025
•
Matt Maisel
30
2
6
The Agent Trust Equation: Reliability and Governance Are the Path to Meaningful Autonomy
Trust = Reliability + Governance
Dec 2, 2025
•
Josh Devon
8
2
See all
Secure Trajectories by Sondera
The Sondera team’s research and analysis on the systems and mechanics of agent control.
Subscribe
Recommendations
View all 12
AI Supremacy
Michael Spencer
One Useful Thing
Ethan Mollick
The Security Industry
Richard Stiennon
AI Pioneers at Work
Jess Leão
Joshua Saxe
Joshua Saxe
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts