LLM Attack Surface Mapper for AI Security Testing
Project description
# ๐ก๏ธ LLMASM - LLM Attack Surface Mapper
> Every Prompt Is An Attack Surface
โโโโโโ โโโ โโโโโโโโโโโโโโโโ โโโโโโโ
โโโโโโโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโ โโโโโโโโโโโโโโ โโโ
โโโโโโโโโโโ โโโโโโโโโโโโโโ โโโ
โโโ โโโโโโ โโโโโโโโโโโโโโโโโโโโโโโโ
โโโ โโโโโโ โโโโโโโโโโโโโโโโ โโโโโโโ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโ
โโโโฃ AI SENTINEL โ โโโ
โ โโโโโโโโโโโโโโโโโ โ
โ โ โ โ
โ โผ โ
โ โฒ___โฑ โ
โโโโโโโโโโโโโโโโโโโโโโโ
โ โ
โโโโโโโโโฉโโโโโโโโฉโโโโโโโโ
โ LLMASM CORE ENGINE โ
โโโโโโโโโโโโโโโโโโโโโโโโโ
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
Framework : LLM Attack Surface Mapper
Version : v1.0.0
Author : Ananya Chatterjee
GitHub : https://github.com/Ananya-0306
LinkedIn : https://www.linkedin.com/in/ananya-chatterjeee/
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
[โ] Prompt Injection Detection
[โ] Jailbreak Discovery
[โ] Tool Abuse Analysis
[โ] Agent Chain Mapping
[โ] System Prompt Exposure
[โ] Risk Scoring Engine
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
"Every Prompt Is An Attack Surface"
โโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโโ
๐ AI Security Reconnaissance Framework
LLMASM is an offensive security framework designed to discover, map and analyze attack surfaces in AI-powered applications.
Unlike traditional reconnaissance tools, LLMASM focuses on identifying:
- AI Attack Surface Reconnaissance
- JavaScript Reconnaissance
- Prompt Injection Discovery
- AI Attack Surface Graph
- HTML & JSON Report Generation
- Risk Scoring Engine
๐ฃ๏ธ Roadmap
- Playwright Support
- Agent Discovery
- RAG Discovery
- MCP Discovery
- Tool Enumeration
Built for:
- Security Researchers
- Red Teams
- AI Security Engineers
- Bug Bounty Hunters
- Product Security Teams
Support If LLMASM helped your research:
โญ Star the repository ๐ด Fork the project ๐ก๏ธ Contribute AI security detections
Mapping the attack surface of the next generation of applications.
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
llmasm_ananya-0.3.0.tar.gz
(11.3 kB
view details)
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 llmasm_ananya-0.3.0.tar.gz.
File metadata
- Download URL: llmasm_ananya-0.3.0.tar.gz
- Upload date:
- Size: 11.3 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a6e92932738bf202009c0f18915b7544265961817a93cd8bdb72253853fa961f
|
|
| MD5 |
d37926f38b2983f2d3c30d34129fc58b
|
|
| BLAKE2b-256 |
d5faa1a814d2c433a2ad379594f60e03d1c728cc924088cae20e523a09aff3d0
|
File details
Details for the file llmasm_ananya-0.3.0-py3-none-any.whl.
File metadata
- Download URL: llmasm_ananya-0.3.0-py3-none-any.whl
- Upload date:
- Size: 16.4 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.9.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
a8a709788b90cc0c12cdf2c57b92f4fc644a8fe72e9264bfe3307e288a2f9a20
|
|
| MD5 |
3c9de4afcb12810ec3de94d8d7747212
|
|
| BLAKE2b-256 |
6028f675d3aa41db351b296fcb5e8d206e176c1fdd606812458a14ff921e98b9
|
