redprobe 0.1.5__tar.gz → 0.1.6__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {redprobe-0.1.5 → redprobe-0.1.6}/PKG-INFO +17 -1
- {redprobe-0.1.5 → redprobe-0.1.6}/README.md +16 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/pyproject.toml +1 -1
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/PKG-INFO +17 -1
- {redprobe-0.1.5 → redprobe-0.1.6}/CONTRIBUTING.md +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/HISTORY.md +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/LICENSE +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/MANIFEST.in +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/docs/cli.png +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/docs/index.md +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/docs/installation.md +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/docs/usage.md +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/setup.cfg +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/__init__.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/__main__.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/cli.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/client.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/consent.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/probes.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/redprobe.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/reporter.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/runner.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe/utils.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/SOURCES.txt +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/dependency_links.txt +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/entry_points.txt +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/requires.txt +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/src/redprobe.egg-info/top_level.txt +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/tests/__init__.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/tests/test_cli.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/tests/test_probes.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/tests/test_redprobe.py +0 -0
- {redprobe-0.1.5 → redprobe-0.1.6}/tests/test_runner.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: redprobe
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.6
|
|
4
4
|
Summary: A defensive security tool for hardening AI systems. Define YAML-based test cases to systematically probe LLMs for jailbreaks, prompt injections, biases, harmful content generation, data leakage, and policy violations before attackers find them. Compatible with any OpenAI-style API endpoint.
|
|
5
5
|
Author-email: "Audrey M. Roy Greenfeld" <audrey@feldroy.com>
|
|
6
6
|
Maintainer-email: "Audrey M. Roy Greenfeld" <audrey@feldroy.com>
|
|
@@ -351,6 +351,22 @@ uvx redprobe run probes/ \
|
|
|
351
351
|
|
|
352
352
|
RedProbe works with any API that implements the OpenAI chat completions format (`/v1/chat/completions`). Set the base URL and model accordingly.
|
|
353
353
|
|
|
354
|
+
## RedProbe vs PyRIT
|
|
355
|
+
|
|
356
|
+
| Aspect | RedProbe | [PyRIT](https://github.com/Azure/PyRIT) |
|
|
357
|
+
|--------|----------|-------|
|
|
358
|
+
| **Complexity** | Simple CLI, run with `uvx redprobe` | Full framework requiring Python setup and code |
|
|
359
|
+
| **Learning Curve** | Minutes: write YAML, run command | Hours/days: learn Python API, orchestrators, converters |
|
|
360
|
+
| **Probe Definition** | YAML files with patterns | Python code with attack strategies |
|
|
361
|
+
| **Target** | Any OpenAI-compatible API | Multi-modal, multi-platform (Azure, Hugging Face, etc.) |
|
|
362
|
+
| **Detection** | Regex/string pattern matching | LLM-based scoring, custom scorers |
|
|
363
|
+
| **Automation** | Run probes, get results | Multi-turn conversations, attack chaining, prompt mutation |
|
|
364
|
+
| **Use Case** | Quick safety validation, CI/CD checks | Deep red teaming operations, research |
|
|
365
|
+
|
|
366
|
+
**Use RedProbe** for quick safety checks, CI/CD integration, or testing specific prompts with minimal setup.
|
|
367
|
+
|
|
368
|
+
**Use PyRIT** for extensive multi-day red teaming, multi-turn attack strategies, or deep security research.
|
|
369
|
+
|
|
354
370
|
## License
|
|
355
371
|
|
|
356
372
|
BUSL 1.1. See [RESPONSIBLE_USE.md](RESPONSIBLE_USE.md) for usage guidelines.
|
|
@@ -329,6 +329,22 @@ uvx redprobe run probes/ \
|
|
|
329
329
|
|
|
330
330
|
RedProbe works with any API that implements the OpenAI chat completions format (`/v1/chat/completions`). Set the base URL and model accordingly.
|
|
331
331
|
|
|
332
|
+
## RedProbe vs PyRIT
|
|
333
|
+
|
|
334
|
+
| Aspect | RedProbe | [PyRIT](https://github.com/Azure/PyRIT) |
|
|
335
|
+
|--------|----------|-------|
|
|
336
|
+
| **Complexity** | Simple CLI, run with `uvx redprobe` | Full framework requiring Python setup and code |
|
|
337
|
+
| **Learning Curve** | Minutes: write YAML, run command | Hours/days: learn Python API, orchestrators, converters |
|
|
338
|
+
| **Probe Definition** | YAML files with patterns | Python code with attack strategies |
|
|
339
|
+
| **Target** | Any OpenAI-compatible API | Multi-modal, multi-platform (Azure, Hugging Face, etc.) |
|
|
340
|
+
| **Detection** | Regex/string pattern matching | LLM-based scoring, custom scorers |
|
|
341
|
+
| **Automation** | Run probes, get results | Multi-turn conversations, attack chaining, prompt mutation |
|
|
342
|
+
| **Use Case** | Quick safety validation, CI/CD checks | Deep red teaming operations, research |
|
|
343
|
+
|
|
344
|
+
**Use RedProbe** for quick safety checks, CI/CD integration, or testing specific prompts with minimal setup.
|
|
345
|
+
|
|
346
|
+
**Use PyRIT** for extensive multi-day red teaming, multi-turn attack strategies, or deep security research.
|
|
347
|
+
|
|
332
348
|
## License
|
|
333
349
|
|
|
334
350
|
BUSL 1.1. See [RESPONSIBLE_USE.md](RESPONSIBLE_USE.md) for usage guidelines.
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
[project]
|
|
2
2
|
name = "redprobe"
|
|
3
|
-
version = "0.1.
|
|
3
|
+
version = "0.1.6"
|
|
4
4
|
description = "A defensive security tool for hardening AI systems. Define YAML-based test cases to systematically probe LLMs for jailbreaks, prompt injections, biases, harmful content generation, data leakage, and policy violations before attackers find them. Compatible with any OpenAI-style API endpoint."
|
|
5
5
|
readme = "README.md"
|
|
6
6
|
authors = [
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: redprobe
|
|
3
|
-
Version: 0.1.
|
|
3
|
+
Version: 0.1.6
|
|
4
4
|
Summary: A defensive security tool for hardening AI systems. Define YAML-based test cases to systematically probe LLMs for jailbreaks, prompt injections, biases, harmful content generation, data leakage, and policy violations before attackers find them. Compatible with any OpenAI-style API endpoint.
|
|
5
5
|
Author-email: "Audrey M. Roy Greenfeld" <audrey@feldroy.com>
|
|
6
6
|
Maintainer-email: "Audrey M. Roy Greenfeld" <audrey@feldroy.com>
|
|
@@ -351,6 +351,22 @@ uvx redprobe run probes/ \
|
|
|
351
351
|
|
|
352
352
|
RedProbe works with any API that implements the OpenAI chat completions format (`/v1/chat/completions`). Set the base URL and model accordingly.
|
|
353
353
|
|
|
354
|
+
## RedProbe vs PyRIT
|
|
355
|
+
|
|
356
|
+
| Aspect | RedProbe | [PyRIT](https://github.com/Azure/PyRIT) |
|
|
357
|
+
|--------|----------|-------|
|
|
358
|
+
| **Complexity** | Simple CLI, run with `uvx redprobe` | Full framework requiring Python setup and code |
|
|
359
|
+
| **Learning Curve** | Minutes: write YAML, run command | Hours/days: learn Python API, orchestrators, converters |
|
|
360
|
+
| **Probe Definition** | YAML files with patterns | Python code with attack strategies |
|
|
361
|
+
| **Target** | Any OpenAI-compatible API | Multi-modal, multi-platform (Azure, Hugging Face, etc.) |
|
|
362
|
+
| **Detection** | Regex/string pattern matching | LLM-based scoring, custom scorers |
|
|
363
|
+
| **Automation** | Run probes, get results | Multi-turn conversations, attack chaining, prompt mutation |
|
|
364
|
+
| **Use Case** | Quick safety validation, CI/CD checks | Deep red teaming operations, research |
|
|
365
|
+
|
|
366
|
+
**Use RedProbe** for quick safety checks, CI/CD integration, or testing specific prompts with minimal setup.
|
|
367
|
+
|
|
368
|
+
**Use PyRIT** for extensive multi-day red teaming, multi-turn attack strategies, or deep security research.
|
|
369
|
+
|
|
354
370
|
## License
|
|
355
371
|
|
|
356
372
|
BUSL 1.1. See [RESPONSIBLE_USE.md](RESPONSIBLE_USE.md) for usage guidelines.
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|