AI Dev Impact Lab JA
← Topics ranking · 2026-08
GITHUB TOPIC

#jailbreak

GitHub repositories that have self-applied the topic "jailbreak" — a creator-tagged metadata that surfaces how AI projects describe themselves.

5
tagged repos
14
top 5 stars
0
with tool sigs
5
shown

REPOS Repos for #jailbreak (top 5 by stars)

NovaCode37/claude-security-skills

Production-ready Claude Code skills for cybersecurity — secret scanning, SAST, prompt-injection testing, HTTP/JWT/dependency auditing. Zero dependencies.

Python 11 AI 100
prat3ik/evalbot

EvalBot — local-first chatbot security & quality evaluation (FastAPI + Next.js). Evaluate chatbot answers against your own docs & guidelines with ML/NLP + AI-judge scoring. Apache-2.0.

Python 3 AI 70
SamsonCyber/llm-injection-field-guide

Dark Promptery: 324 LLM prompt-injection techniques, crosswalked to OWASP/MITRE ATLAS/NIST/CWE.

HTML 0 AI 100 Solo live ↗
rosscyking1115/redteam-foundry

LLM red-team evaluation harness — prompt injection, refusal, leakage and staleness, with cross-judge validation and attack-corpus audits.

Python 0 AI 70
yeodh10/prompt-guard

Prompt Injection Guard - a defense-in-depth (rules + LLM) demo that detects and blocks prompt-injection / jailbreak attempts in LLM user input (Streamlit + Claude).

Python 0 AI 70

RELATED Other topics · full topics ranking →

#claude-code

1,564

#ai-agents

1,160

#llm

1,071

#claude

943

#python

806

#ai

741

#developer-tools

728

#mcp

727

#codex

521

Aggregated by case-insensitive match against topics_json of each repo's latest content snapshot. methodology