Skip to content
codethor0Public

About

Researcher profile

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 

Repository files navigation

Thor Thor

Independent security researcher. I work on containment and verification of autonomous AI agents, cryptographic interlocks, and reproducible security research.

ORCID THOR-SEC

Research is published openly under CC BY 4.0 with code under MIT, and every paper has a public repository of reproducible artifacts. This work was conducted independently and is not affiliated with or representative of any employer.

Publications

Paper DOI Artifacts
NIGHTCRAWLER: Temporal Causal Closure for Persistent and Deferred Effects of Autonomous AI Agents 10.5281/zenodo.23265287 nightcrawler
The Agent Security Control Plane: Toward a Zero-Trust Architecture for Autonomous Machine Cognition 10.5281/zenodo.23146801 agent-security-control-plane
Containing Cyber-Capable AI Agents 10.5281/zenodo.23124432 ccaa
Memory-Egress Cryptographic Interlock (MECI) 10.5281/zenodo.23109676 meci
Attack Calculus: A Typed, Evidence-Aware State-Transition Calculus for Cross-Domain Cybersecurity Reasoning 10.5281/zenodo.23092790 attack-calculus
Mission-Invariant Architecture Morphing (MIAM) 10.5281/zenodo.23001045 miam

Selected projects

  • llm-agent-control-plane: defensive reference implementation that keeps authorization, policy, approval, and audit logging outside the model for tool-connected LLM agents.
  • model-identity-verifier: command-line tool that checks whether a language model identifies itself consistently and flags route, provider, or downgrade signals.
  • rte-a-reference: reference implementation of the Red Team Engineering Algorithm with attributed tasking, tamper-evident audit logs, and ephemeral infrastructure.
  • db-access-lab: disposable PostgreSQL lab for evaluating third-party products that request database access.
  • dockercomms: OCI-native secure file transport with signed artifacts.

OpenAI Academy credentials

Course credentials issued by OpenAI Academy through Accredible. Each entry links to its verification record on credential.net. Listing them does not imply affiliation with or endorsement by OpenAI.

Credential Issuer Issued Verification
Scale Codex Across Teams and Systems OpenAI Academy November 18, 2026 credential.net
Extend Codex Workflows OpenAI Academy November 18, 2026 credential.net
Get Started with Codex OpenAI Academy November 18, 2026 credential.net
Optimize AI Application Performance OpenAI Academy November 17, 2026 credential.net
Build with Retrieval-Augmented Generation OpenAI Academy November 17, 2026 credential.net
Design and Build Agentic Systems OpenAI Academy November 16, 2026 credential.net
Evaluate AI Applications OpenAI Academy November 16, 2026 credential.net
Scope AI Solutions OpenAI Academy November 16, 2026 credential.net
Agents and Workflows OpenAI Academy October 4, 2026 credential.net
Applied AI Foundations OpenAI Academy October 4, 2026 credential.net
AI Foundations OpenAI Academy October 4, 2026 credential.net
AI Leadership OpenAI Academy October 3, 2026 credential.net

Links

About

Researcher profile

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Sponsor this project

Packages

Contributors