- Home
- AI Security Testing Tools
- Basilisk
Basilisk
What it is
Basilisk is an open-source framework for authorized security testing, vulnerability research, and academic study of AI and LLM systems. It includes 32 attack modules across eight categories mapped to the OWASP LLM Top 10. Its Smart Prompt Evolution engine combines 15 mutation operators, five crossover strategies, and multi-signal fitness scoring. Multi-turn tests address prompt cultivation, authority escalation, and sycophancy exploitation, with guardrail drift monitoring. Basilisk connects to OpenAI, Anthropic, Google, xAI Grok, Groq, Azure OpenAI, GitHub Models, Ollama, and custom HTTP or WebSocket endpoints. Reports are available in HTML, SARIF 2.1.0, JSON, Markdown, and PDF. GitHub Actions and GitLab CI integrations can use SARIF output and fail pipelines on critical findings. Install options include desktop packages for Windows, macOS, and Linux, pip, Docker, and source. The CLI needs Python 3.11 or later and an API key for the provider under test. Prompt evolution, payload mutation, and report generation run locally. The software is free under AGPL-3.0; testing systems not owned by the user requires explicit written authorization.
For and against
For
- Includes 32 modules across eight OWASP-mapped categories.
- Supports multiple named providers and custom endpoints.
- Exports reports in five formats.
- Offers GitHub Actions and GitLab CI integration.
- Prompt evolution and report generation run locally.
Against
- CLI requires Python 3.11 or higher.
- CLI requires an API key for the provider tested.
- Testing systems not owned requires written authorization.
- Released under the AGPL-3.0 license.
The verdict
Basilisk provides broad LLM red-team coverage, provider connections, and CI reporting in a free, locally run framework. Users should confirm their authorization and license requirements before adopting it.
Who it suits
It suits security researchers, AI developers, and academic users conducting authorized LLM assessments. Users need a compatible provider API key for the CLI and written permission before testing systems they do not own.
Plans and prices
AGPL-3.0 open-source software
CLI, Desktop, Docker, or source distribution · authorized use only
Read 30 Sep 2026 · basilisk.rothackers.com
On the record
- Attack modules
- It includes 32 attack modules across 8 categories mapped to the OWASP LLM Top 10.basilisk.rothackers.com · read 30 Sep 2026
- Authorized use
- Users must obtain explicit written authorization before testing AI or LLM systems they do not own.basilisk.rothackers.com · read 30 Sep 2026
- CI/CD
- GitHub Actions and GitLab CI integration uses SARIF output and can fail pipelines on critical findings.basilisk.rothackers.com · read 30 Sep 2026
- Install methods
- The project provides Windows, macOS, and Linux desktop packages, a pip CLI, Docker images, and source installation.basilisk.rothackers.com · read 30 Sep 2026
- License
- Basilisk is released under the AGPL-3.0 license, permitting use, copying, modification, and distribution subject to the license and terms.basilisk.rothackers.com · read 30 Sep 2026
- Local processing
- Prompt evolution, payload mutation, and report generation run entirely on the user's local machine.basilisk.rothackers.com · read 30 Sep 2026
- Multi-turn testing
- Multi-turn modules perform prompt cultivation, authority escalation, and sycophancy exploitation with guardrail drift monitoring.basilisk.rothackers.com · read 30 Sep 2026
- Prerequisites
- The CLI requires Python 3.11 or higher and an API key for the LLM provider being tested.basilisk.rothackers.com · read 30 Sep 2026
- Privacy
- The CLI and Desktop app do not send telemetry, scan results, API keys, or personal data to Basilisk.basilisk.rothackers.com · read 30 Sep 2026
- Prompt evolution
- Its Smart Prompt Evolution engine uses 15 mutation operators, 5 crossover strategies, and multi-signal fitness scoring.basilisk.rothackers.com · read 30 Sep 2026
- Provider integrations
- It supports OpenAI, Anthropic, Google, xAI Grok, Groq, Azure OpenAI, GitHub Models, Ollama, and custom HTTP or WebSocket endpoints.basilisk.rothackers.com · read 30 Sep 2026
- Purpose
- Basilisk is an open-source AI/LLM red teaming framework for authorized security testing, vulnerability research, and academic study.basilisk.rothackers.com · read 30 Sep 2026
- Reports
- Basilisk exports HTML, SARIF 2.1.0, JSON, Markdown, and PDF reports.basilisk.rothackers.com · read 30 Sep 2026
- Supply-chain security
- The project says it uses signed releases and verified checksums, while cautioning that it cannot guarantee absolute security.basilisk.rothackers.com · read 30 Sep 2026
- Support
- Security issues and privacy questions can be reported to [email protected].basilisk.rothackers.com · read 30 Sep 2026
