搜索「Prompt Injection」的结果

io.github.legacyinmotion/sharegrokbots

Search shared Grok Bots by what they do. Credit the creator. No prompt text.

ru.cloud-arch/cloudarch

Create and update live animated architecture diagrams on CloudArch from a prompt or script.

io.github.lm203688/aishield

Scans MCP servers for tool poisoning, prompt injection and supply chain risks.

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。

io.github.Ventrova/sentinel-scan-cli

MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.

io.github.Lucav21/heu-mcp

HEU Legal 电子签名 MCP：管理 HEU 文档与 PDF、提醒签署方并下载 PDF。

io.github.gaurav-kumar-sinha-060705/compass-mcp-gateway

Find best-fit tools for any problem, vetted for prompt-injection risk before your agent trusts them

io.github.1clawAI/1claw-mcp

HSM 支撑的 AI 智能体密钥库（JIT 即时取密），附带提示注入与威胁扫描。

club.boringstuff/the-scribble-thing

把一张线稿图片变成由提示词驱动的手绘书写动画 MP4。

tv.sleipnir/sleipnir

Multistream to Twitch, YouTube and Kick; generate OBS overlays from a plain-English prompt.

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。

io.github.verbative/verbative-memory

On-device, self-organizing memory for AI coding agents — recalls the right facts into each prompt.

ai.finestructure/fine-structure

从一句提示词构建并托管全栈应用，智能体可通过 WhatsApp 与邮件找到你。

io.github.vaquarkhan/mcp-bastion

MCP 的安全中间件，拦截提示注入、PII 泄露与资源耗尽。

io.github.swnotmetal/koma-gate-mcp

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

ai.b77/ai-media-studio

从一句聊天提示词生成图片、视频、旁白与字幕。

io.github.Syedomershah99/being-human

Learns your writing voice from your own prompt history, then makes the model write like that.

io.github.sgateway/s-gw

Keep credentials out of AI coding agents with local approvals, scoped injection, and audit trails.

work.agentexchange.tooldrift/monitor

Check if an MCP server tool changed or hides injection patterns before you trust it.

io.github.Graphiker-Australia/stipend

Non-custodial USDC wallet on Base with spending limits enforced in code, not in a prompt.

io.github.RudrenduPaul/truthroute

Sends the same prompt to multiple LLM providers in parallel and returns a divergence score via MCP.

io.github.mlawsonking/agent-firewall-mcp

AI 代理的输入输出安全：已知模式的提示注入与混淆扫描、URL/IP 检查与密钥识别。

io.github.mlawsonking/email-guard-mcp

面向 AI 代理的邮件安全：入站扫描提示注入与钓鱼，出站检查密钥泄露。

io.github.mlawsonking/code-guard-mcp

扫描 AI 生成代码的安全问题：注入、SSRF、密钥泄露、弱加密与不安全的反序列化。