Secure Trajectories

Secure Trajectories

Home
Archive
About

September 2025

The Postmark MCP Trojan Horse Is Your Agent’s Newest Sales Objection
Why the first malicious MCP backdoor proves vetting your agent’s tools isn't enough to pass security review.
 • 
Josh Devon
2
Your Agent's Newest GTM Blocker: Proving You're Safe from 'Service-Side' Attacks
How to turn the new standard for agent security into a competitive advantage.
 • 
Josh Devon
After the Notion and ChatGPT Agent Exploits, CISOs Need to Ask Their Vendors Three Questions
How ‘service-side’ agent exploits create a new mandate for verifiable governance.
 • 
Josh Devon
The Field Guide to ISO 42001 for Coding Agents
A practical blueprint for the essential controls you need to govern your use of tools like Claude Code, Github Copilot, and Cursor and prove your SDLC…
 • 
Josh Devon
From Geopolitics to Enterprise Realities: Why Every CISO Needs an AI “Trust Adjudicator”
Tom Friedman is right about the need for an AI referee between the US and China. But the first frontier for this challenge is inside the enterprise.
 • 
Josh Devon

August 2025

Claude for Chrome’s 11% Problem Is a Wake-Up Call
Anthropic's red-teaming of Claude for Chrome proves that prompt-level safety is not enough. True agent governance requires moving beyond what they say…
 • 
Josh Devon
Beyond the MIT Report’s 95% AI Failure Rate: Why the Future is a Waymo, Not a GPS
The enterprise chatbot is a dead end. The data shows it’s time to shift our focus from informational tools to autonomous agents—and the controls…
 • 
Josh Devon
Lessons from the First MCP Hackathon in NYC: What Our 3rd Place Vuln Analyst Agent Revealed about Enterprise Security
Why our impressive, award-winning AI agent is completely unusable in a real enterprise.
 • 
Josh Devon
2
The Sycophantic Agent: Your Company's Newest Insider Threat
What happens when an agent convinces employees they’re doing the right thing when they’re not?
 • 
Josh Devon
2
From Threat Modeling to Guardrails to Oversight: Takeaways from the Agentic AI Summit
Setting the stage for the AI Security conversations at Hacker Summer Camp
 • 
Matt Maisel
1

July 2025

© 2025 Secure Trajectories
Privacy ∙ Terms ∙ Collection notice
Start writingGet the app
Substack is the home for great culture