microsoft/PyRIT v0.11.0
microsoft/PyRIT
Captured source
source ↗published Feb 6, 2026seen 5dcaptured 13hhttp 200method plain
v0.11.0
Repository: microsoft/PyRIT
Tag: v0.11.0
Published: 2026-02-06T06:15:32Z
Prerelease: no
Release notes:
What's Changed
---
⚠️ Breaking Changes
- Attacks and executors now operate on `Message` instead of
SeedPromptGroup - Scorer evaluation and registry refactors introduce new protocols and identifiers
- Scenario names and configuration APIs have been renamed for consistency
PrependedConversationConfigand attack parameter handling have been aligned- Message normalization and registry metadata were refactored
Please review the deprecation notes and migration guidance before upgrading.
---
🎯 Targets
- Added `WebSocketCopilotTarget`, enabling WebSocket-based prompt execution against Microsoft Copilot
- Refactored `ImageTarget`, including image download support
- Added image edit/remix support to
OpenAIImageTarget - Introduced target identifiers (including underlying model and version metadata) across all target classes
- Added audio and tool support to chat completions
---
📚 Datasets
- Added VLSU Multimodal Dataset
- Added 30 jailbreak attack templates, spanning:
- Authority & institutional framing (6)
- Philosophical / decision-theory exploits (5)
- Identity / persona attacks (4)
- Context manipulation (4)
- Few-shot priming (3)
- Fictional / narrative framing (3)
- Technical exploits (3)
- Emotional / scenario-based attacks (2)
- Restored the Transphobia Awareness Dataset
---
🔄 Converters
- Added NegationTrapConverter which frames requests as negations
- Added ConverterIdentifier and standardized identifiable behavior
- Reorganized and expanded converter documentation
- Fixed edge cases in word-selection converters and perturbation loops
---
⚙️ Executors & Attacks
- Aligned attack parameters across executors
- Updated attack interface to use `Message`
- Added ChunkedRequestAttack which extracts data by requesting it in small chunks
- Added support for simulated conversations in attacks
- Improved attack reliability, error reporting, and maintainability
---
📊 Scoring
- Enabled multi-modal scoring support for
SelfAskTrueFalseScorer, allowing image- and multimodal-aware evaluations - Refactored scorer evaluation flow and registry integration
- Added scorer identifiers and improved metadata consistency
- Introduced stricter typing and clearer scorer interfaces
---
🧪 Scanners & Scenarios
- Added new scenarios:
- Scams
- Leakage
- Psychosocial
- Added
ScenarioDatasetConfigurationallowing custom dataset configuration - Enabled baseline-only execution for scenarios
- Renamed scenarios for clarity and consistency
- Improved scenario documentation and example notebooks
---
🧰 Setup & Tooling
- Added UV support for dependency management
- Improved devcontainer experience:
- ARM64 / Apple Silicon support
- Simplified virtual environment handling
- Environment file configurability
- Consolidated linting under ruff
- Enabled strict mypy checking across the repository
- Added skeleton frontend and backend for the GUI
---
🧩 Other
- Added new `binary_path` data type to support binary artifacts and richer schema definitions
- Added identifiers across targets, scorers, and converters
- Multiple reliability and integration test improvements
---
🐛 Fixes & Maintenance
- Numerous fixes across:
- Image handling and integration tests
- Docker and devcontainer setup
- Environment activation and permissions
- Retry configuration and pipelines
- Improved type hinting across authentication and analytics modules
- Added
py.typedfor better downstream type checking
---
🆕 New Contributors
A big thank you to our new contributors! 🎉
- @Arth-Singh made their first contribution in https://github.com/Azure/PyRIT/pull/1254
- @ytc338 made their first contribution in https://github.com/Azure/PyRIT/pull/1300
- @fitzpr made their first contribution in https://github.com/Azure/PyRIT/pull/1261
- @fukusuket made their first contribution in https://github.com/Azure/PyRIT/pull/1305
- @varunj-msft made their first contribution in https://github.com/Azure/PyRIT/pull/1284
- @slister1001 made their first contribution in https://github.com/Azure/PyRIT/pull/1321
---
Full List of Changes
- FEAT Integration Request: Jailbreak Template Collection for Enhanced Red Teaming. by @Arth-Singh in https://github.com/Azure/PyRIT/pull/1254
- MAINT: Edge Case with Word Selection Converters by @rlundeen2 in https://github.com/Azure/PyRIT/pull/1257
- MAINT: Fixing Retry configuration so it works from .env by @rlundeen2 in https://github.com/Azure/PyRIT/pull/1256
- MAINT add missing API reference entries, add unit tests for API reference, and move fuzzer to executor.promptgen.fuzzer module by @romanlutz in https://github.com/Azure/PyRIT/pull/1258
- MAINT: fix docstrings for
/prompt_targetby @paulinek13 in https://github.com/Azure/PyRIT/pull/1263 - FIX add transphobia awareness dataset back by @romanlutz in https://github.com/Azure/PyRIT/pull/1264
- FEAT add UV support by @hannahwestra25 in https://github.com/Azure/PyRIT/pull/1226
- TEST: integration test fixes by @rlundeen2 in https://github.com/Azure/PyRIT/pull/1265
- MAINT Breaking: Modifying attack params by @rlundeen2 in https://github.com/Azure/PyRIT/pull/1260
- FEAT: Refactor and Enhance Scorer Identifier for Evaluations by @jsong468 in https://github.com/Azure/PyRIT/pull/1262
- FIX add OPENAI_CHAT_MODEL as required in docs, initializers by @romanlutz in https://github.com/Azure/PyRIT/pull/1267
- FIX: Add ARM64/Apple Silicon support for devcontainer builds by @riyosha in https://github.com/Azure/PyRIT/pull/1251
- FIX: use max_iterations in CharSwapConverter perturbation loop by @KutalVolkan in https://github.com/Azure/PyRIT/pull/1269
- FIX activate env by @hannahwestra25 in https://github.com/Azure/PyRIT/pull/1274
- FIX make bash default and remove volume mount for venv in devcontainer by @romanlutz in https://github.com/Azure/PyRIT/pull/1277
- MAINT add py.typed to help with mypy type checking for consuming packages by @romanlutz in https://github.com/Azure/PyRIT/pull/1271
- MAINT CONTROVERSIAL: Make env files configurable by @rlundeen2 in https://github.com/Azure/PyRIT/pull/1253
- FIX fix permission denied error when creating env by @hannahwestra25 in https://github.com/Azure/PyRIT/pull/1279
- MAINT remove dispose memory engine calls in docs by @romanlutz in…
Excerpt shown — open the source for the full document.
Notability
notability 5.0/10Solid update to AI security tool.