Injectcheck runs on your own machine — the client starts it, so there is no endpoint to ping. 2 128 installs a week from npm. Last commit 23 Oct 2026.
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
Today is the operative word: we check Injectcheck every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add injectcheck -- npx -y @reneturcios/injectcheck
{
"mcpServers": {
"injectcheck": {
"command": "npx",
"args": [
"-y",
"@reneturcios/injectcheck"
]
}
}
}
[mcp_servers.injectcheck]
command = "npx"
args = ["-y", "@reneturcios/injectcheck"]
{
"mcpServers": {
"injectcheck": {
"command": "npx",
"args": [
"-y",
"@reneturcios/injectcheck"
]
}
}
}
{
"servers": {
"injectcheck": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@reneturcios/injectcheck"
]
}
}
}
Scan AI agent skills and configs for hidden Unicode, prompt injection and exfiltration.
Scan any public URL for hidden instructions aimed at AI agents (prompt injection). Free, no auth.
Scan a page for hidden prompt-injection payloads targeting AI agents.
Check text before your agent reads it: hidden instructions, invisible text and links that leak data.
Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Scans untrusted web pages, emails, MCP responses, or A2A payloads for hidden prompt injections an.
Answers built from our own checks of this server.