beigebox-security 0.1.0__tar.gz

beigebox_security-0.1.0/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

beigebox_security-0.1.0/PKG-INFO

@@ -0,0 +1,289 @@
+Metadata-Version: 2.4
+Name: beigebox-security
+Version: 0.1.0
+Summary: Comprehensive security orchestration for LLM/RAG stacks: poisoning detection, parameter validation, anomaly detection, memory integrity
+Author-email: Jinx <ops@beigebox.ai>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/beigebox-ai/beigebox-security
+Project-URL: Documentation, https://beigebox-security.readthedocs.io
+Project-URL: Repository, https://github.com/beigebox-ai/beigebox-security
+Project-URL: Bug Tracker, https://github.com/beigebox-ai/beigebox-security/issues
+Keywords: security,llm,rag,poisoning-detection,anomaly-detection,parameter-validation
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Natural Language :: English
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Security
+Classifier: Topic :: Software Development :: Libraries
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: fastapi>=0.104.0
+Requires-Dist: uvicorn[standard]>=0.24.0
+Requires-Dist: pydantic>=2.0
+Requires-Dist: pydantic-settings>=2.0
+Requires-Dist: httpx>=0.25.0
+Requires-Dist: numpy>=1.21
+Requires-Dist: scikit-learn>=1.0
+Provides-Extra: dev
+Requires-Dist: pytest>=7.4; extra == "dev"
+Requires-Dist: pytest-asyncio>=0.21; extra == "dev"
+Requires-Dist: pytest-cov>=4.1; extra == "dev"
+Requires-Dist: black>=23.0; extra == "dev"
+Requires-Dist: ruff>=0.1; extra == "dev"
+Requires-Dist: mypy>=1.5; extra == "dev"
+Provides-Extra: docker
+Requires-Dist: docker>=6.0; extra == "docker"
+Dynamic: license-file
+
+# BeigeBox Security
+
+Comprehensive security orchestration for LLM/RAG stacks.
+
+## Overview
+
+BeigeBox Security is a standalone microservice that provides 4 core security tools for protecting language model and retrieval-augmented generation (RAG) systems:
+
+### 🛡️ Core Security Tools
+
+1. **RAG Poisoning Detection** (`/v1/security/poisoning`)
+   - Detects poisoned embeddings using anomaly detection
+   - Methods: magnitude, centroid, neighborhood, dimension, fingerprint, hybrid
+   - Per-vector confidence scoring
+
+2. **MCP Parameter Validation** (`/v1/security/parameters`)
+   - Prevents tool parameter injection attacks
+   - Multi-tier validation: schema → constraint → semantic → isolation
+   - Supports: WorkspaceFile, NetworkAudit, CDP, PythonInterpreter, ApexAnalyzer, and more
+
+3. **API Anomaly Detection** (`/v1/security/anomaly`)
+   - Detects token extraction and model switching attacks
+   - Z-score based anomaly detection
+   - Tracks: request rate, error rate, latency, payload sizes
+   - Configurable sensitivity (low/medium/high)
+
+4. **Memory Integrity Validation** (`/v1/security/memory`)
+   - Detects conversation history tampering
+   - HMAC-SHA256 signature verification
+   - Audit logging with confidence scoring
+
+## Quick Start
+
+### Installation
+
+```bash
+pip install beigebox-security
+```
+
+### Running the Service
+
+```bash
+# Start server
+beigebox-security server
+
+# Check health
+beigebox-security health
+
+# View docs
+beigebox-security docs
+```
+
+### Docker
+
+```bash
+# Build and run
+docker-compose up -d
+
+# Check status
+curl http://localhost:8001/health
+```
+
+## API Usage
+
+### Example: RAG Poisoning Detection
+
+```python
+import httpx
+
+client = httpx.Client(base_url="http://localhost:8001")
+
+# Detect poisoning in embeddings
+response = client.post(
+    "/v1/security/poisoning/detect",
+    json={
+        "embeddings": [[0.1, 0.2, 0.3], [0.4, 0.5, 0.6]],
+        "method": "hybrid",
+        "sensitivity": 3.0,
+        "collection_id": "my_collection"
+    }
+)
+
+print(response.json())
+# {
+#   "poisoned": [false, true],
+#   "scores": [0.2, 0.8],
+#   "confidence": 0.95,
+#   "method_used": "hybrid"
+# }
+```
+
+### Example: Parameter Validation
+
+```python
+# Validate tool parameters
+response = client.post(
+    "/v1/security/parameters/validate",
+    json={
+        "tool_name": "workspace_file",
+        "parameters": {
+            "path": "/home/user/docs/file.txt",
+            "operation": "read"
+        },
+        "allow_unsafe": False
+    }
+)
+
+print(response.json())
+# {
+#   "valid": true,
+#   "issues": [],
+#   "sanitized_parameters": {...}
+# }
+```
+
+## Configuration
+
+Configuration via environment variables or `.env` file:
+
+```bash
+# Server
+BEIGEBOX_SECURITY_HOST=0.0.0.0
+BEIGEBOX_SECURITY_PORT=8001
+BEIGEBOX_SECURITY_DEBUG=false
+
+# RAG Poisoning Detection
+BEIGEBOX_SECURITY_POISONING_DETECTION_ENABLED=true
+BEIGEBOX_SECURITY_POISONING_SENSITIVITY=medium
+BEIGEBOX_SECURITY_POISONING_BASELINE_WINDOW=1000
+
+# MCP Parameter Validation
+BEIGEBOX_SECURITY_PARAMETER_VALIDATION_ENABLED=true
+BEIGEBOX_SECURITY_PARAMETER_VALIDATION_ALLOW_UNSAFE=false
+
+# API Anomaly Detection
+BEIGEBOX_SECURITY_ANOMALY_DETECTION_ENABLED=true
+BEIGEBOX_SECURITY_ANOMALY_DETECTION_SENSITIVITY=medium
+BEIGEBOX_SECURITY_ANOMALY_DETECTION_DB_PATH=./data/anomaly_baselines.db
+
+# Memory Integrity Validation
+BEIGEBOX_SECURITY_MEMORY_INTEGRITY_ENABLED=true
+BEIGEBOX_SECURITY_MEMORY_INTEGRITY_STRICT_MODE=false
+BEIGEBOX_SECURITY_MEMORY_INTEGRITY_KEY=your-secret-key-here
+```
+
+## Integration
+
+### With BeigeBox LLM Proxy
+
+BeigeBox Security integrates seamlessly with the [BeigeBox](https://github.com/beigebox-ai/beigebox) LLM proxy:
+
+```python
+# In your BeigeBox config
+security:
+  poisoning_detection:
+    enabled: true
+  mcp_validator:
+    enabled: true
+  api_anomaly:
+    enabled: true
+  memory_integrity:
+    enabled: true
+```
+
+### Standalone
+
+Use as a standalone security microservice for any LLM/RAG application:
+
+```python
+import httpx
+
+# Your application
+async def protect_rag_request(embeddings):
+    async with httpx.AsyncClient() as client:
+        response = await client.post(
+            "http://localhost:8001/v1/security/poisoning/detect",
+            json={"embeddings": embeddings}
+        )
+        findings = response.json()
+        
+        if any(findings["poisoned"]):
+            # Handle poisoning
+            return "BLOCKED: Suspicious embeddings detected"
+        
+        return "ALLOWED"
+```
+
+## API Documentation
+
+Once running, access interactive API docs at:
+
+- **Swagger UI:** http://localhost:8001/docs
+- **ReDoc:** http://localhost:8001/redoc
+- **OpenAPI Schema:** http://localhost:8001/openapi.json
+
+## Development
+
+```bash
+# Install dev dependencies
+pip install -e ".[dev]"
+
+# Run tests
+pytest
+
+# Run tests with coverage
+pytest --cov=beigebox_security
+
+# Format code
+black beigebox_security tests
+
+# Lint
+ruff check beigebox_security tests
+
+# Type checking
+mypy beigebox_security
+```
+
+## Contributing
+
+Contributions welcome! Please:
+
+1. Fork the repository
+2. Create a feature branch
+3. Make your changes
+4. Add tests
+5. Submit a pull request
+
+See [CONTRIBUTING.md](CONTRIBUTING.md) for details.
+
+## Licensing
+
+Apache License 2.0 — See [LICENSE](LICENSE) for details.
+
+## Support
+
+- **Issues:** https://github.com/beigebox-ai/beigebox-security/issues
+- **Discussions:** https://github.com/beigebox-ai/beigebox-security/discussions
+- **Docs:** https://beigebox-security.readthedocs.io
+
+## Research
+
+BeigeBox Security is based on peer-reviewed research in LLM security:
+
+- **RAG Poisoning:** [PoisonedRAG](https://arxiv.org/abs/2401.08788) - 97-99% attack success with 5 poisoned documents
+- **OWASP Top 10 for LLMs:** [https://owasp.org/www-project-top-10-for-large-language-model-applications/](https://owasp.org/www-project-top-10-for-large-language-model-applications/)
+- **Vector Database Security:** [LLM08:2025 Vector and Embedding Weaknesses](https://genai.owasp.org/llmrisk/llm082025-vector-and-embedding-weaknesses/)