7 tagged Prompt Injection, measured the same way as everything else here.
Plugin Claude Code
Bundles 1 skill, 5 commands, 1 MCP server · 52 tokens together
Real-time safety scanning for LLM interactions. Detects prompt injection, PII leaks, harmful content, toxicity, obfuscation, secrets, and dangerous tool calls — 600-case benchmark at 100% accuracy with sub-millisecond latency.
Plugin Claude Code
Bundles 34 skills, 4 MCP servers · 626 tokens together
Offline AI/LLM security scanner: prompt injection, MCP command injection and tool poisoning, RAG leaks, poisoned Agent Skills. Scan code, or check a skill/MCP server before you install it.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 32 tokens together
LangGraph proof and native audit with source-bound resume-parity evidence before review.
Plugin Gemini CLI
A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain.
Plugin Claude Code
Bundles 1 skill · 99 tokens together
AIShield security scanner for MCP servers, AI Skills, and agent workspaces. Covers OWASP MCP Top 10 + OWASP Agentic AI Top 10 + sandbox hardening. Zero-dependency, local-first, offline-capable.