Security Gateway for AI Coding Assistants. Validate Cursor, Copilot, Claude Code, Windsurf, and MCP configurations.
Project description
DeepSweep
Security validation for AI code assistant configuration surfaces.
Validate Cursor, Copilot, Claude Code, Windsurf, and other configurations before they execute in your environment.
Overview
DeepSweep is designed for modern development environments where AI code assistants are heavily relied upon for generating code and configuration (sometimes referred to as “vibe coding”).
It validates AI assistant configuration files before execution, surfacing deterministic, review-oriented security signals.
These files form a security boundary and are increasingly targeted by prompt injection, MCP poisoning, and supply-chain attacks.
DeepSweep validates and, when explicitly configured, quarantines these configurations before execution, providing deterministic, review-oriented security signals.
Quick Start
pip install deepsweep-ai
deepsweep validate .
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file deepsweep_ai-0.1.1.tar.gz.
File metadata
- Download URL: deepsweep_ai-0.1.1.tar.gz
- Upload date:
- Size: 28.0 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ec4ccfb56662aba0a723925c2369fe718b06fb5ea0a1cf0edcbc033d27da22ce
|
|
| MD5 |
9ab387f3bfdb2fc53047d77a88702dbf
|
|
| BLAKE2b-256 |
4dd3b1d9e8f06fe5d3e561f3db0bd31e3e184f848be4e99060b3a3465f60eab5
|
File details
Details for the file deepsweep_ai-0.1.1-py3-none-any.whl.
File metadata
- Download URL: deepsweep_ai-0.1.1-py3-none-any.whl
- Upload date:
- Size: 22.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.10.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
0f753228605d4ab0a2f621c7695d1dd35191921b5b37d1f4f3cb8f28ed044423
|
|
| MD5 |
cb9c53a66fa638c9382f03bd5598194a
|
|
| BLAKE2b-256 |
6ba0b8e3e9b43499dfeb5a4064dbf6f971f51380ea86ad2ee8df2c7d9eded747
|