Prompt Injection Scanner
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
Open the source (opens github.com) https://github.com/nguyenhieuec/agent-tools-plugins
Before you use it
- Runs on someone else's server: what you send it leaves your machine.
What it is
MCP servers from app.openkrill.
The problem it solves and who it suits haven't been reviewed by InnerVault. The description above is the source's own.
How to get it
Remote endpoint (streamable-http)
https://injectionscan.openkrill.app/mcp
From the server's entry in the official MCP Registry
Related
-
AISafetyHot
MCP serversAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.
git clone https://github.com/wuyoscar/AISafetyHot.git -
prompt-injection-scanner
MCP serversScans RAG content/scraped pages for indirect prompt injection
@guardbee/mcp-prompt-injection-scanner@0.2.2 -
prompt-injection-scanner
MCP serversScans RAG content/scraped pages for indirect prompt injection
@guardbee/mcp-prompt-injection-scanner@1.2.0 -
Prompt Injection Detector
MCP serversPrompt injection and system-prompt extraction testing for LLM agents. Free 8-probe sample.
-
Habits prompt-injection guard
MCP serversCheck user prompts for injection/jailbreaks; your own guard learns from your labels. Works keyless.
-
Scan web pages, mails, PDFs and tool output for prompt injection before your agent reads them.