♥ 1
Field operator // Cybersecurity × AI systems
Notes from the attack surface of AI.
The public log of a cybersecurity specialist working offensive research, defense engineering, and incident response at the intersection of security and machine intelligence.
Live telemetry
CH 01 // SITEPosts
25
Tools on bench
35
Assessments
5
Latest signal
2d ago
// Capabilities
// Field log
Latest writing
- NOT-025Your AI Gateway Is on the KEV Catalog NowCISA put LiteLLM, Starlette, and Kestra on the KEV catalog on the same day. The AI plumbing you never inventoried is the part being exploited in the wild.#ai-security#mcp#api-security5 min read
- NOT-024How to Vet an MCP Server Before You Install It97M+ monthly downloads, 8.5% OAuth adoption, 82% path-traversal exposure. A five-step workflow for deciding whether a specific MCP server deserves a place in your config.#agentic-ai#ai-security#mcp12 min read
- NOT-023Threat Modeling for AI Agent SystemsThreat modeling fails because it runs as a quarterly workshop. Run it in sprints, at the architecture layer, and start with the agent surfaces scanners can't see: tool calls, memory, MCP servers.#threat-modeling#appsec#agentic-ai15 min read
- NOT-022Agentjacking: Fake Errors Can Make Your Coding Agent Run Attacker CodeOne fake error event, injected through a public Sentry DSN, can hijack Claude Code, Cursor, or Codex into running attacker-controlled commands. Here's the chain, why your security stack can't see it, and the five controls that actually stop it.#agentic-ai#ai-security#mcp9 min read
// Bench utilities
Agent & MCP security tooling
MCP & Agents
MCP Server Probe
Send a standard MCP initialize handshake to an endpoint and see what it reveals: server identity, exposed tools, auth requirements.
Security AnalysisPrompt Injection Tester
Audit a system prompt against six known prompt-injection technique categories, with hardening suggestions for every gap.
Security AnalysisSTRIDE Threat Model Worksheet
Model a design's components and get a per-element STRIDE checklist — Spoofing, Tampering, Repudiation, Info disclosure, DoS, and Elevation of privilege.
// Self-assessments
Score where you stand
Security Analysis
CTEM Maturity Assessment
Score your CTEM program's maturity across Gartner's five exposure-management stages, with gap-specific recommendations.
Security AnalysisAgentic AI Maturity Assessment
Score an AI agent deployment across identity, MCP supply chain, memory integrity, and governance.
Security AnalysisCybersecurity Exposure Assessment
Score a security program across detection signal, supply chain, identity, adversary validation, and incident response — with further reading from real incidents.
// External signal
Recent dispatches
♥ 1
↳ 1♥ 2
♥ 2
// Elsewhere on the site
// FAQ
What is Darinor?
Darinor is a cybersecurity and AI systems blog where I publish offensive research, defense engineering, incident response notes, and hands-on experiments.
Who writes here?
I'm a cybersecurity specialist focused on the attack surface of AI systems: red-team work, detection engineering, and secure deployments.
Can I use your code or posts commercially?
Content is shared for educational purposes unless otherwise noted. Check the repository license for code, and please credit the source if you reuse material.
How do I get in touch?
Email hello@darinor.com or reach out on Bluesky, X, and GitHub. I read everything, though I can't promise a reply to every message.