revsmoke/prompt-rejector
v1.2.0ISC
Screen prompts, skills and MCP tools with TypeSafe judgments and configurable reasoning models.
MCP servers
Declared configuration, as published in mcp.json. The directory shows indexed content; it never connects to or executes these servers.
prompt-rejectorstdio
{
"type": "stdio",
"command": "node",
"args": [
"${PLUGIN_ROOT}/scripts/launch.mjs"
]
}What this package declares
The files a client reads when it loads this plugin, exactly as this revision carries them.
{
"$schema": "https://agent-plugins.org/schemas/1.0.0/plugin.schema.json",
"name": "prompt-rejector",
"version": "1.2.0",
"description": "Screen prompts, skills and MCP tools with TypeSafe judgments and configurable reasoning models.",
"author": {
"name": "Bryan Rice"
},
"homepage": "https://github.com/revsmoke/promptrejectormcp",
"repository": "https://github.com/revsmoke/promptrejectormcp",
"license": "ISC",
"keywords": [
"security",
"mcp",
"prompt-injection",
"typesafe"
],
"extensions": {
"com.openai": {
"interface": {
"displayName": "Prompt Rejector",
"shortDescription": "Check prompts, skills and tool descriptions.",
"longDescription": "Run Prompt Rejector locally, inspect untrusted text, and review security decisions using active TypeSafe judgments and configurable reasoning models. Scans send content to configured providers.",
"developerName": "Bryan Rice",
"category": "Productivity",
"capabilities": [
"Read",
"Write"
],
"websiteURL": "https://github.com/revsmoke/promptrejectormcp",
"defaultPrompt": [
"Use Prompt Rejector to check this prompt.",
"Set up Prompt Rejector and verify its MCP tools.",
"Scan this SKILL.md with Prompt Rejector."
]
}
}
}
}
What else this package ships
These files come with the package and this site does not publish them. They are listed so you know what is there before you install it.
- openai.yaml
Client extensions
Data this package carries for particular clients. The directory lists the clients named and never reads what is addressed to them.
- com.openai