Building the security layer for AI agent work.
I'm Gustavo Aragón, founder of Oktsec. I build security infrastructure for AI agents operating across code, tools, credentials, packages and infrastructure. My work combines runtime governance and verifiable evidence through Oktsec, open source security through Aguara and nanostack, and hands-on vulnerability research across the agent ecosystem.
The agent ecosystem
Security findings reported through major disclosure programs.
Reports to notable vendors and formal disclosure programs (VRP / MSRC), across agent tooling, CLIs and infrastructure. The recurring failure modes from that research feed directly into the controls we build at Oktsec and the detection logic in Aguara.
Reported through programs including
- Microsoft
- Stripe
- Cloudflare
- AWS
- Mercury
Selected writing
View all →I called the lack of agent identity a security crisis. A2A shipped signed Agent Cards, MCP shipped Enterprise-Managed Authorization, and research delivered task-scoped tokens. A scorecard of what got built and what is still missing.
- 2026 · 07Community · 3 minJoining the first cohort of Agentic AI Foundation ambassadorsThe Agentic AI Foundation, a Linux Foundation initiative, put MCP under open governance and opened its first ambassador program. What that means for agent infrastructure and security.
- 2026 · 07Opinion · 3 minWorking with AI agents doesn't remove the mental load, it transforms itThe real challenge of working with AI isn't the model of the week, it's how we manage our energy and time in a reality that never rests. How I'm organizing work in loops of intensity and rest.
- 2026 · 07Opinion · 6 minNo AI sovereignty without infrastructure sovereigntyFrom 'Atoms for Peace' to frontier-model export controls: why AI sovereignty is decided in the infrastructure, not in model access.
What I work on
Products & research
View all →- OktsecThe security platform for AI agent work. Oktsec helps teams define policy, govern approved execution environments and verify the evidence produced by agents across code, tools, credentials and infrastructure.Security platform · Runtime policy · Evidence →
- AssessmentA structured security review of software systems, automation paths, MCP servers and agent workflows. You get reviewed findings with severity and evidence, plus clear priorities and next steps.Oktsec · Findings · Evidence →
- SignalSecurity intelligence for the agent ecosystem. Signal maps risk across public agent tooling, MCP servers, developer CLIs, automation paths and repositories, turning ecosystem activity into security intelligence for builders and teams.Oktsec · Ecosystem monitoring · Supply chain →
- AguaraOpen source security engine for AI agents and software supply chains. Aguara checks what projects and agents are about to trust before installation, delegation or execution: packages, lockfiles, install scripts, MCP configurations, agent skills and tools, package-manager policy and CI workflows. Signed threat intelligence and deterministic behavioral analysis, local and offline by default, with no SaaS account, telemetry or LLM calls.Open source · Pre-execution security · Supply chain →
- nanostackA local delivery workflow for AI coding agents: scope, plan, build, review, security, QA and ship. Every step leaves reviewable evidence in plain files on disk, with no cloud or hidden runtime.Open source · Agent workflows · Local artifacts →