1. Conduid
  2. RAG
  3. Prompt Armor
MCP server · RAG

Prompt Armor

Open-source prompt injection detector — 5 layers, 91.7% F1, ~27ms, offline, Apache 2.0

39Low

Scored 7 hours ago · breakdown

About Prompt Armor

Prompt Armor is an MCP server in the RAG category: open-source prompt injection detector — 5 layers, 91.7% F1, ~27ms, offline, Apache 2.0. It has been installed 0 times through Conduid.

Install

Clone
git clone https://github.com/prompt-armor/prompt-armor

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

Ask AI about Prompt Armor

Powered by Claude · Grounded in docs

I know everything about Prompt Armor. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • ·Scoped permissionsNot checked yet.
Questions

About Prompt Armor

How do I install Prompt Armor?

Run git clone https://github.com/prompt-armor/prompt-armor, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is Prompt Armor safe to use with an AI agent?

Its trust score is 39 out of 100 (low). Conduid hasn't run static security checks on this repository yet, so review the source yourself before granting it credentials. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Prompt Armor still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.