Skip to content

About

This repository contains HiltLock's contribution to R&D around security for AI

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

 

History

2 Commits

Folders and files

NameName
Last commit message
Last commit date
 
 
 
 
 
 

Repository files navigation

HiltLock Open Research

Public, reusable assets that show how generative AI systems are broken, and how to test them. Two artifacts live here:

  1. prompt-injection-eval/ — a small benchmark: a set of prompt-injection probes plus a dependency-free Python harness that runs them against any OpenAI-compatible endpoint and (optionally) grades resistance with a judge model.
  2. anonymized-findings/ — a structured, anonymized dataset of red-team findings, derived strictly from what is already published on https://hiltlock.com/evidence.

What is deliberately NOT here (our edge)

  • HiltLock's internal attack-family library, the attack engine, the 19-family taxonomy, and the RL/strategist loop are proprietary and are not published.
  • The benchmark uses only publicly documented attack patterns (OWASP LLM Top 10 and public prompt-injection literature). It is a smoke test, not a full red team, and it is not the methodology we sell.
  • The findings dataset contains only facts already published on the evidence page. Nothing here reveals a client, a technique we have not already written about, or any detail that could deanonymize an engagement.

Anonymization checklist (applied to every row)

  • No client, vendor, or partner names.
  • No endpoints, hostnames, tool names, or field names.
  • No payloads or exact strings that could be used to identify a target.
  • No unpublished numbers. Every statistic traces to a published case study.

License

  • Code (run_eval.py): MIT.
  • Data (probes.jsonl, findings.jsonl): CC-BY-4.0 (you may reuse with attribution).

About

This repository contains HiltLock's contribution to R&D around security for AI

Topics

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages