EasyJailbreak vs agentic_security
LLM jailbreak research and security scanning compared
EasyJailbreak and agentic_security are Python tools for testing LLM behavior with adversarial prompts. EasyJailbreak focuses on reusable attack components and evaluation, while agentic_security centers on configurable scans against HTTP endpoints and agent workflows, including CI use.
EasyJailbreak: Build and Evaluate LLM Jailbreak Attacks
EasyJailbreak is a Python framework for assembling and testing jailbreak methods against language models. It suits researchers and developers who need reusable attack components and a structured way to evaluate model responses.
agentic_security: Scan LLMs and Agent Workflows for Vulnerabilities
Agentic Security is a Python vulnerability scanner and red-teaming kit for LLMs and agent workflows. It runs prompt-based scans against HTTP APIs, using supplied or built-in datasets to probe jailbreaks, fuzzing, and multimodal inputs.
| EasyJailbreak | agentic_security | |
|---|---|---|
| Language | Python | Python |
| License | GPL-3.0 | Apache-2.0 |
| Stars | 914 | 2k |
| Forks | 92 | 305 |
| Last analyzed | Oct 3, 2026 | Nov 11, 2026 |
Key differences
- EasyJailbreak organizes experiments around attack recipes and reusable selectors, mutators, constraints, and evaluators; agentic_security configures scans using prompt datasets, mutations, thresholds, and request templates.
- EasyJailbreak supports Hugging Face models and several cloud-hosted model integrations; agentic_security sends probes to a configured HTTP endpoint.
- EasyJailbreak reports prompts, target responses, and evaluation scores; agentic_security documents probes for text, image, and audio inputs and CI-oriented scanning.
- EasyJailbreak is licensed under GPL-3.0; agentic_security is licensed under Apache-2.0.
- EasyJailbreak lists 914 stars and 92 forks; agentic_security lists 2k stars and 292 forks.
Choose EasyJailbreak if you…
- need reusable components for assembling and comparing jailbreak attacks.
- want to run included attack recipes or build custom ones for LLM security research.
- need reports with prompts, model responses, and evaluation scores.
Choose agentic_security if you…
- want to scan a model or application through a configured HTTP API.
- need repeatable security checks integrated into CI.
- want to probe agent workflows or documented image and audio interfaces.
Compare the numbers side by side, or add more projects
This comparison is generated with AI from the OSRepos analyses of both projects. Always check each project's repository and documentation before choosing.