io.github.bch1212/injectshieldai

injectshield

Verified · 2 mo ago

Prompt-injection firewall for AI agents — scan untrusted text before LLM calls.

Install

claude mcp add injectshield -- npx -y @injectshield/[email protected]

Requires: INJECTSHIELD_API_KEY, INJECTSHIELD_API_BASE

Our take

This server scans untrusted text for prompt-injection risk before passing it to a model, positioning itself as a defensive layer in agent pipelines. It is for teams exposing agents to scraped pages, user uploads, or other external content. The problem is real, but products in this space often overclaim, so the right expectation is a partial filter rather than a complete firewall.

reviewed by hand · 2026-07-12

Something wrong or dead here? Report it

Verification record

last verified
2 mo ago
github stars
0
last commit
6 mo ago
archived
no
license
MIT
downloads / wk
24
latest version
0.1.4
in registry since
2026-05-06

github.com/bch1212/injectshield

reaai

REA

Verified · 35 days ago

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

hand-reviewed291k stars232k dl/wkchecked 35 days ago

rufloai

Ruflo

Verified · 10 days ago

Agent teams, swarms, memory and hooks for Claude Code and Codex, served over MCP.

hand-reviewed81k stars72k dl/wkchecked 10 days ago

claude-flowai

claude-flow

Verified · 2 mo ago

AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.

hand-reviewed73k stars19k dl/wkchecked 2 mo ago

tldrawai

tldraw

Verified · 2 mo ago

Draw and visually collaborate with your agents on tldraw's canvas.

hand-reviewed50k starschecked 2 mo ago

codebase-memory-mcpai

Codebase Memory

Verified · 2 mo ago

Codebase knowledge graph for AI agents — 162 languages, sub-ms queries, 99% fewer tokens.

hand-reviewed45k stars12k dl/wkchecked 2 mo ago

openseoai

OpenSEO

Verified · 6 days ago

Keyword research, site audits, rank tracking and AI visibility for your AI agent.

hand-reviewed28k starschecked 6 days ago