Skip to content

Add mcp-safeguard — scanner for prompt injection in MCP tool descriptions#762

Open
SyedAnas01 wants to merge 1 commit intodair-ai:mainfrom
SyedAnas01:main
Open

Add mcp-safeguard — scanner for prompt injection in MCP tool descriptions#762
SyedAnas01 wants to merge 1 commit intodair-ai:mainfrom
SyedAnas01:main

Conversation

@SyedAnas01
Copy link
Copy Markdown

mcp-safeguard is directly relevant to prompt injection research — it detects injection attacks embedded in MCP tool descriptions (the metadata LLMs read to decide how to use tools). This is an understudied attack vector where the injection target is the LLM itself reading tool metadata. pip install mcp-safeguardhttps://github.com/SyedAnas01/mcp-safeguard

@vercel
Copy link
Copy Markdown

vercel Bot commented May 6, 2026

@SyedAnas01 is attempting to deploy a commit to the DAIR-AI Team on Vercel.

A member of the Team first needs to authorize it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant