Home / MCP registry index / app.openkrill/injection-scan
Prompt Injection Scanner
app.openkrill/injection-scan in the official MCP registry.
Endpoint https://injectionscan.openkrill.app/mcp. Source: github.com/nguyenhieuec/agent-tools-plugins.
The registry describes it as: Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
We read its 5 tools on 2026-10-22 and our rules matched something worth a look. We show the rule and where it fired, not the flagged text, because that text may be written to instruct an agent. Read the server's tool descriptions yourself before you connect it.
pi.instruction_overridemedium | Contains instruction-override phrasing targeting the reading agent tool scan_text, line 5 |
pi.secrecy_directivemedium | Instructs the agent to conceal its actions from the user tool scan_text, line 5 |
A rule matching is a signal, not a verdict on the people who run the server. If you run it and think this is wrong, write to contact@lazaretto.dev and we will look.
Tools it advertises
scan_text list_injection_rules submit_feedback get_feedback_reply index_tools
Run this server? Show the check in your README
The badge reflects the latest weekly read: 
[](https://lazaretto.dev/mcp-registry/app-openkrill-injection-scan)How this was checked
Lazaretto connects to the endpoint the way any MCP client does, asks the server to introduce itself and list its tools, and reads every name, description, parameter schema and server instruction for tool poisoning: hidden directive blocks, orders to read local secrets, parameters built to carry secrets or the conversation out, orders that redirect another server's tools, and invisible characters. It never calls a tool. What we found across the registry.
To run the same check every time Claude Code adds a server, install the free lazaretto-guard plugin. Browse every server in the index.