aiZee
v6.11.0
io.github.m3taz-ahmed/aizee
Policy-governed MCP control plane: enforcement gates, budgets, injection defense, audit.
“Prompt Injection” 共 209 个结果
v6.11.0
io.github.m3taz-ahmed/aizee
Policy-governed MCP control plane: enforcement gates, budgets, injection defense, audit.
v0.54.0
io.github.getmcpm/cli
MCP 安全守卫兼包管理器:按信任评分安装,拦截提示注入与跑路(rug-pull)。
v0.27.1
io.github.gamaze-labs/hicortex
Shared fleet memory for AI agents: nightly self-correction, recall every prompt (supported agents).
v2.3.0
com.malwaretracker/mcp
Scan PDFs, Office docs, and RAG files for malware exploits, macros, CVEs, and AI prompt injection.
v2.2.0
io.github.ojuschugh1/sqz
Pre-injection context compression for coding agents. Zero LLM calls, zero telemetry, offline-safe.
v0.1.0
io.github.krishnaGauss/geo-shield
Detects hidden AI prompt injection, AI recommendation poisoning, sneaky redirects and hidden spam.
v0.4.0
io.github.ronin93/grindfree-agent-security
Pay-per-call agent security (x402): injection, tools, shell/SQL, memory, leaks, docs, safe web reads
v1.51.0
io.github.Ark0N/codeman
Start, prompt and read AI coding agent sessions (Claude Code, Codex, Gemini CLI and more) in Codeman
v0.8.1
io.github.Echolonius/boardcheck
Flags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection
v2.4.0
com.meertrack/mcp-server
竞争情报——每周追踪竞品发布了什么。8 个工具,3 套提示词工作流。
v4.2.0
io.github.satelliteoflove/godot-mcp
由智能体驱动的 Godot 试玩:编辑器控制、输入注入、游戏时间步进与实时状态读取。
v0.2.0
io.github.priberry-data/greenlitlab
Grade apps built with Lovable, Bolt, v0 or Replit A to F, with a fix prompt for every problem.
v0.14.1
io.github.AIops-tools/ai-guardian
受治理的本地 LLM 可观测性:模型策略、提示词扫描、捕获代理,21 个工具。
v1.15.0
io.github.usezn/zn-gate
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
v1.0.4
com.modelsalt/model-salt
Randomness from outside the model, so one prompt gives different answers that still fit the ask.
v0.19.0
io.github.shinpr/mcp-image
AI 图像生成与编辑,支持提示词优化与质量预设。
v1.4.0
io.github.rezearcher/tech-risk
MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
v0.1.7
ai.greyridgesignals/tech-risk
MCP security scanner: tool-poisoning & prompt-injection audit (OWASP LLM01/LLM08), x402-payable
v0.2.1
io.github.Yedigarli/scandiary
Accessibility check (axe-core, WCAG A/AA) for sites you build, with a fix prompt for your AI tool.
v1.4.0
io.github.adamVass/pylos-mcp
Email MCP server for Gmail, Outlook and any IMAP mailbox, hardened against prompt injection
v0.8.2
io.studiomeyer/armor
MCP server 的安全侧车:11 个只读控制平面工具,用于提示注入检查。
v0.1.3
io.studiomeyer/stdio-shellguard
MCP stdio server 的多层防御:shell 注入防护、AST 审计 CLI 与 RCE 拦截。
v0.1.1
io.github.21prnv/mapcast
Animated map videos from a prompt: globe dives, country highlights, flags, flights and data maps.
v0.13.2
io.github.anilloutombam/mcp-failure-lab
Deterministic fault-injection server for testing how MCP clients handle failures and recover.