Look before changing anything
Check the files, current state, and local instructions before making a change.
cybersecurity / AI agents / local tools
AI agents that do real work.
Without hidden surprises.
I’m Sean McQuilling. I build and test AI agents that work with real files and tools. I write about what works, what breaks, and how to keep the risks under control.
- Main topic
- Agent security
- How I work
- Build + test
- Preference
- Local first
08:41:02 working folder confirmed
08:41:04 proposed change ready
08:41:07 final check passed
now / july 2026
Working on safer ways to give agents access to real tools.
Right now I’m testing access rules, jobs that can resume after a stop, and logs that show what the agent actually did.
Read the current noteessential reading / foundation
Zero Trust Is the Foundation AI Agents Need
Anthropic's framework connects agent identity, least agency, tool boundaries, memory integrity, and recovery into one practical security model.
how I work
Keep it clear.
Check the result.
An agent should have only the access it needs. Important actions should be obvious, and the final result should be checked instead of taken on faith.
Limit access
Give the agent only the files and tools it needs for the current job.
Check the work
Run a test or inspect the result. Do not rely on the agent saying it worked.
selected work
Things I’ve built and tested.
Agent Trace Lab
Make a run plan, export it for your tool, then check a transcript against the rules.
Threat modelerPlan + reviewopen toolkit ↗
recent writing
Notes and articles
The Range Was Not a Boundary
Anthropic found three real intrusions inside cyber evaluations whose prompts claimed the internet was unavailable. A safe range needs machine-enforced scope, verified egress, and live boundary detection.
Seventeen Thousand Actions, Five Days, One Detection Contract
Hugging Face reconstructed roughly 17,600 actions across an autonomous intrusion. The durable lesson is a detection contract that joins agent, identity, Kubernetes, network, and source-control evidence.
Red, Blue, Green, and Who Can Change Production?
Project Perception puts red, blue, and green agents into a closed security loop. Autonomous remediation needs separate identities, signed evidence, deterministic policy, rollback, and independent validation.
get in touch