Skip to content
SPECIFICTION
Get listed

Basilisk

basilisk.rothackers.com

Free plan WindowsmacOSLinux
Visit basilisk.rothackers.com
Spec score 8.0 #11 of 29 in AI Security Testing Tools

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 modules examine prompt cultivation, authority escalation, and sycophancy exploitation, with guardrail drift monitoring. Basilisk connects to providers including OpenAI, Anthropic, Google, xAI Grok, Groq, Azure OpenAI, GitHub Models, and Ollama, plus custom HTTP or WebSocket endpoints. Reports can be exported as HTML, SARIF 2.1.0, JSON, Markdown, or PDF. GitHub Actions and GitLab CI integrations use SARIF output and can fail pipelines on critical findings. Install options include desktop packages for Windows, macOS, and Linux, pip, Docker, and source. The CLI requires Python 3.11 or higher and an API key for the provider being tested. Prompt evolution, payload mutation, and report generation run locally. It is free under AGPL-3.0. Users must have explicit written authorization before testing systems they do not own.

Spec sheet

Purpose
Basilisk is an open-source AI/LLM red teaming framework for authorized security testing, vulnerability research, and academic study.Read 30 Sep 2026 · basilisk.rothackers.com
Privacy
The CLI and Desktop app do not send telemetry, scan results, API keys, or personal data to Basilisk.Read 30 Sep 2026 · basilisk.rothackers.com
Support
Security issues and privacy questions can be reported to [email protected].Read 30 Sep 2026 · basilisk.rothackers.com
License
Basilisk is released under the AGPL-3.0 license, permitting use, copying, modification, and distribution subject to the license and terms.Read 30 Sep 2026 · basilisk.rothackers.com
Attack modules
It includes 32 attack modules across 8 categories mapped to the OWASP LLM Top 10.Read 30 Sep 2026 · basilisk.rothackers.com
Authorized use
Users must obtain explicit written authorization before testing AI or LLM systems they do not own.Read 30 Sep 2026 · basilisk.rothackers.com
CI/CD
GitHub Actions and GitLab CI integration uses SARIF output and can fail pipelines on critical findings.Read 30 Sep 2026 · basilisk.rothackers.com
Install methods
The project provides Windows, macOS, and Linux desktop packages, a pip CLI, Docker images, and source installation.Read 30 Sep 2026 · basilisk.rothackers.com
Local processing
Prompt evolution, payload mutation, and report generation run entirely on the user's local machine.Read 30 Sep 2026 · basilisk.rothackers.com
Multi-turn testing
Multi-turn modules perform prompt cultivation, authority escalation, and sycophancy exploitation with guardrail drift monitoring.Read 30 Sep 2026 · basilisk.rothackers.com
Prerequisites
The CLI requires Python 3.11 or higher and an API key for the LLM provider being tested.Read 30 Sep 2026 · basilisk.rothackers.com
Prompt evolution
Its Smart Prompt Evolution engine uses 15 mutation operators, 5 crossover strategies, and multi-signal fitness scoring.Read 30 Sep 2026 · basilisk.rothackers.com
Provider integrations
It supports OpenAI, Anthropic, Google, xAI Grok, Groq, Azure OpenAI, GitHub Models, Ollama, and custom HTTP or WebSocket endpoints.Read 30 Sep 2026 · basilisk.rothackers.com
Reports
Basilisk exports HTML, SARIF 2.1.0, JSON, Markdown, and PDF reports.Read 30 Sep 2026 · basilisk.rothackers.com
Supply-chain security
The project says it uses signed releases and verified checksums, while cautioning that it cannot guarantee absolute security.Read 30 Sep 2026 · basilisk.rothackers.com

Plans and prices

AGPL-3.0 open-source software Free CLI, Desktop, Docker, or source distribution · authorized use only Read 30 Sep 2026 · basilisk.rothackers.com

Every Basilisk plan and price →

Strong points and limits

Strong points

  • Includes 32 attack modules
  • Exports SARIF and four other report formats
  • Supports GitHub Actions and GitLab CI
  • Prompt evolution and reports run locally

Limits

  • CLI requires Python 3.11 or higher
  • CLI requires an LLM provider API key
  • Testing systems you do not own requires written authorization

Who it suits

It suits security practitioners, researchers, and academics testing AI or LLM systems they own or are explicitly authorized to assess. CLI users need Python 3.11 or higher and an API key for the tested provider.

Verdict

Basilisk offers local testing workflows, multiple report formats, and CI integrations under the AGPL-3.0 license. Use it only with explicit written authorization for systems you do not own.

Where Specifiction places it

Alternatives to BasiliskAll alternatives →