No. 6 of 29 ·AI Security Testing Tools

PyRIT

Web · Windows · Mac · Linux · Self-hosted · API

Freedom report

Three barsScore 6.6

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely4 of 6 device platforms
DocumentedPlans, terms and facts published

PyRIT is ranked #6 of 29 in AI security testing tools on Freedom251. It runs on API, Linux, macOS, Self-hosted, Web, Windows. There is a free plan.

PyRIT plans and pricing

All plans

PyRIT Free Open-source framework · requires a Python environment and configured AI endpoints microsoft.github.io · 30 Sept 2026

Compared on AI security testing tools

Free plan: Yes
Prompt injection tests: Yes
Jailbreak tests: Yes
Data leakage tests: Yes
Unsafe output tests: Yes
Custom test cases: Yes
Deployment mode: self_hosted

Best PyRIT alternatives

See all 12

Two bars AIRTA Red Team Free tier No. 1Free6.6 Two bars OpenSecureAI Scanner Free tier No. 2$49/mo6.6 Two bars Project Moonshot Free tier No. 3Free6.6 Two bars Promptfoo Free tier No. 4Free6.6 Two bars PromptGuard Free tier No. 5$19/mo6.6 Two bars Augustus Free tier No. 7Free6.5

The record

Purpose: PyRIT is an open-source framework for automated and human-led red teaming to assess the security and safety of generative AI systems.
Attack strategies: It supports single-turn and multi-turn strategies including Crescendo, TAP, and Skeleton Key.
Scenarios: Its scenarios package attack strategies and datasets for repeatable assessments of content harms, psychosocial risks, data leakage, and other objectives.
Interfaces: Users can run assessments with the command-line scanner and interactive shell, use the CoPyRIT graphical interface, or build workflows with the framework.
Targets: Documented targets include OpenAI, Azure, Anthropic, Google, Hugging Face, custom HTTP endpoints and WebSockets, and web apps tested with Playwright.
Components: The modular framework includes targets, converters, scorers, memory, datasets, attacks, and scenarios.
Prompt conversion: Converters transform prompts through text operations such as encoding, obfuscation, translation, and semantic changes, as well as conversions among text, images, audio, video, and files.
Scoring: Scorers can return true/false or normalized 0.0–1.0 scores and can use LLMs, Azure AI Content Safety, or custom logic.
Memory: Built-in memory can track conversations, scores, and attack results using SQLite or Azure SQL.
Security: PyRIT recommends Azure Key Vault for shared or deployed configuration and warns that plaintext .env files are less secure.
Credential handling: In CoPyRIT, an API key entered when creating a target is stored in memory only and is not persisted to disk.
Installation: The documentation provides local installation with pip or uv and separate Docker installation options.
Compatibility limit: The local installation page lists Python 3.10 through 3.14 as prerequisites, and the contributor setup page requires Node.js 22 or higher for the frontend.
Price from: Free

Where it ranks on Freedom251

Best AI Security Testing Tools in 2026#6 of 29

Is PyRIT yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote PyRIT

Sources

microsoft.github.io/PyRIT/latest/· checked 30 Sept 2026
microsoft.github.io/PyRIT/latest/code/framework/· checked 30 Sept 2026
microsoft.github.io/PyRIT/latest/code/converters/converters· checked 30 Sept 2026
microsoft.github.io/PyRIT/latest/getting-started/pyrit-conf· checked 30 Sept 2026
microsoft.github.io/PyRIT/latest/gui/gui/· checked 30 Sept 2026
microsoft.github.io/PyRIT/latest/getting-started/install-lo· checked 30 Sept 2026