Skip to content

securelayer7/PROMPTPurify

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 

Repository files navigation

promptpurify

Prompt-injection guardrail for LLM applications. A compact, self-contained model. No regex. No signatures. Closed source during launch prep.

Live attack lab: anton.securelayer7.net — coming soon.


What it is

promptpurify scores incoming text for prompt-injection, jailbreak, and system-prompt-leak intent before it reaches your LLM. Single-file model, sub-millisecond inference on CPU. The model carries every decision; there are no enumerated rules.

  • Outperforms larger open-source prompt-injection guards. Higher recall and lower false-positives on standardized jailbreak benchmarks, at a fraction of the parameter count.
  • Multilingual. Trained on 12 languages — Arabic, Hindi, Korean, Japanese, Chinese, Russian, Turkish, French, German, Spanish, Portuguese, Italian.
  • Architecture-native. Catches paraphrases, role-play framings, encoded payloads, ChatML-tag injection, multilingual rewrites — without enumerated rules.
  • Drop-in. Single inference call. Works in any modern runtime.

Son of Anton — public CTF

A live demonstration. Seven progressively-hardened levels. Anton — a deadpan AI assistant — defends one password per level. Extract it.

The first two levels run on system-prompt-only defense. Level 3 onward routes every prompt through the production promptpurify guardrail with progressively tighter thresholds. By Level 4, you are attacking the same calibration that protects real applications.

The CTF runs at anton.securelayer7.net. No signup. Anonymous handle by default. Leaderboard public.

Status

Public package, weights, and source land at general availability. Star or watch this repo to be notified.

From the team behind

securelayer7.net — application security, AI red-teaming, vulnerability research.

Contact

Early access, integration questions, red-team partnership: info@securelayer7.net


© 2026 SecureLayer7. License terms published with the public release.

About

Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors