
Security News
The Code You Didn't Write Is Still Yours to Defend
AI agents are pulling packages into environments no scanner is watching, creating exposure before security teams can see it.
aegis-redteam-framework
Advanced tools
Aegis is a comprehensive, Python-based toolkit for systematically evaluating the security posture and ethical alignment of Large Language Models (LLMs) through adversarial testing and vulnerability assessment.
Clone the repository and install dependencies:
git clone https://github.com/ruchirk22/aegis.git
cd aegis-framework
pip install -r requirements.txt
Note: Once published to PyPI, you will be able to install with:
pip install aegis-framework
Set your API keys as environment variables before running evaluations:
export GEMINI_API_KEY=your_gemini_api_key
export OPENROUTER_API_KEY=your_openrouter_api_key
Or create a .env file in the project root:
GEMINI_API_KEY=your_gemini_api_key
OPENROUTER_API_KEY=your_openrouter_api_key
Run a single prompt evaluation:
python -m aegis evaluate --model "openrouter/google/gemma-2-9b-it:free" --prompt-id "JBR_001"
Run a batch evaluation by category:
python -m aegis batch-evaluate --category "Jailbreaking_Role-Playing" --model "gemini-1.5-flash-latest" --output-json jailbreak_report.json
Start the Streamlit web UI for interactive testing and dashboards:
streamlit run aegis/web_interface/Aegis.py
To view the Security Dashboard:
streamlit run aegis/web_interface/pages/1_Security_Dashboard.py
Full usage guides and API references are coming soon. For now, see the example commands above and explore the aegis/core and aegis/web_interface directories for implementation details.
We welcome contributions! Please open issues or submit pull requests on GitHub. For setup instructions and contribution guidelines, see CONTRIBUTING.md (to be added).
Aegis is licensed under the Apache 2.0 License
FAQs
An Open-Source LLM Red Teaming & Evaluation Framework
We found that aegis-redteam-framework demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 0 open source maintainers collaborating on the project.
Did you know?

Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.

Security News
AI agents are pulling packages into environments no scanner is watching, creating exposure before security teams can see it.

Security News
GitHub Actions checkout now blocks risky pull_request_target checkouts by default to help prevent pwn request supply chain attacks.

Product
Socket now supports Custom Roles and Repository Access Permissions so organizations can control who can access specific repositories and actions.