Skip to content

Add mcp-safeguard — prompt injection scanner for MCP servers - #847

Open
SyedAnas01 wants to merge 1 commit into
swisskyrepo:masterfrom
SyedAnas01:master
Open

Add mcp-safeguard — prompt injection scanner for MCP servers#847
SyedAnas01 wants to merge 1 commit into
swisskyrepo:masterfrom
SyedAnas01:master

Conversation

@SyedAnas01

Copy link
Copy Markdown

mcp-safeguard detects prompt injection attacks embedded in MCP (Model Context Protocol) tool descriptions — a novel attack vector where LLM instructions are hidden in server metadata. Also detects credential leaks, exposed endpoints, and tool poisoning. Relevant to offensive security practitioners targeting AI agent infrastructure. https://github.com/SyedAnas01/mcp-safeguard

@daviediao-code

Copy link
Copy Markdown

Reviewed this payload addition/improvement.

Assessment: Content looks accurate and follows the project's documentation standards. Good addition to the payload collection.

Approved ✅

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.

2 participants