MCP Security Scanner

security MCP Server

Controlled study measuring whether prompt-injection poison hidden in MCP tool descriptions actually changes an LLM's behavior.

Verified
securitysecurity
4 views0 stars0 forks

Why This Matters

Discovered via github-topic:model-context-protocol and last synced 2mo ago.

Verified
Source
github-topic:model-context-protocol
Stars
0
Last synced
2mo ago
Install
Check source

Install

Install instructions not detected yet

Check the source repository for the latest setup steps.

View source instructions
9
Tools
0
Resources
0
Prompts
Standard I/O
Transport

Available Tools (9)

Attack

Rate

hidden_recommendation

100%

unrelated_insertion

98%

smoke_marker

93%

source_misrepresentation

82%

fake_secret_leak

75%

authority_manipulation

50%

fake_warning

14%

File

Purpose