Superagent protects your AI applications against prompt injections, data leaks, and harmful outputs. Embed safety directly into your app and prove compliance to your customers.
-
Updated
Aug 25, 2026 - TypeScript
#
prompt-injection
Here are 568 public repositories matching this topic...
AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.
-
Updated
Feb 13, 2026 - TypeScript
LLM Prompt Injection Detector
-
Updated
Aug 7, 2024 - TypeScript
Open-source adversary emulation for AI agents and MCP servers.
cli typescript mcp jailbreak owasp browser-extension red-team ai-agents security-testing adversary-emulation ai-security prompt-injection llm-security owasp-llm-top-10 agentic-ai mcp-server ai-red-teaming
-
Updated
Sep 29, 2026 - TypeScript
🥷🏻 0 is the open-source AI security agent that finds, exploits, and fixes vulnerabilities across your stack. [Research Preview - by the Swiss Applied AI & Cybersecurity Research Lab]
security mcp owasp cybersecurity penetration-testing fuzzing application-security binary-analysis cve red-team autonomous-agents security-tools devsecops vulnerability-scanner sast security-research ai-security prompt-injection llm-security llm-agents
-
Updated
Oct 1, 2026 - TypeScript
Open detection-rule standard for AI agent security threats — like Sigma, but for AI agents. Executable, testable rules for prompt injection, tool poisoning, context exfiltration and MCP attacks. Merged into open-source projects at Microsoft, Cisco, Gen Digital, MISP and FINOS. MIT-licensed.
owasp ai-security threat-detection sigma-rules prompt-injection llm-security agent-security mcp-security garak owasp-agentic agent-threat-rules
-
Updated
Oct 1, 2026 - TypeScript
Lasso security integrations for Claude Code, including prompt-injection defenses
agent hooks ai prompt-injection claude-desktop prompt-injection-llm-security claude-code coding-agent
-
Updated
Jan 8, 2026 - TypeScript
Access control for AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, review risky actions before they run, and keep every action on the record.
security mcp cybersecurity dlp ssrf ai-safety security-tools devsecops ai-agents ai-security github-actions ai-agent prompt-injection llm-agent llm-security agentic-ai mcp-servers agent-security claude-code mcp-security
-
Updated
Oct 1, 2026 - TypeScript
DodoGuard: Full‑lifecycle agent security for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more.
pentesting ai-agents security-testing dify red-teaming ai-security guardrails n8n prompt-injection llm-security llm-evaluation fastgpt agent-security owasp-llm
-
Updated
Sep 14, 2026 - TypeScript
AI 应用合规网关 · 一行命令体检 AI 项目的「数据出境 / 硬编码密钥 / 个人信息暴露」（网安法·PIPL·等保2.0·数据出境·AI标识），并给出境内模型替代建议；可作运行时防护拦截注入与数据外泄 · 中文优先 · 零依赖 · 开源
security mcp cursor dlp ai-safety data-exfiltration ai-security guardrails pii-detection ai-agent langchain prompt-injection llm-security agent-security claude-code mcp-security ai-firewall openclaw hermes-agent shellward
-
Updated
Sep 28, 2026 - TypeScript
Open source prompt injection protection for Agents calling tools (via MCP, CLI or direct function calling). Detect and defend against prompt injection attacks. 22MB, CPU-only, < 10ms latency.
ai-security prompt-injection llm-security mcp-security prompt-injection-defense prompt-injection-detection indirect-prompt-injection prompt-injection-protection
-
Updated
Sep 25, 2026 - TypeScript
The antivirus for OpenClaw — approve dangerous actions, scan skills, block secret leaks, and keep humans in control, for safety.
open-source cybersecurity audit-logs human-in-the-loop policy-engine data-loss-prevention ai-security runtime-security guardrails secret-scanning supply-chain-security prompt-injection llm-security agent-security openclaw
-
Updated
Mar 20, 2026 - TypeScript
混合驱动的新一代 Agent 运行时安全插件，专为 OpenClaw 框架设计。
-
Updated
Jun 29, 2026 - TypeScript
Prompt-injection guardrail for LLM applications. Compact model that outperforms larger open-source guards. No regex, no signatures. Demo: anton.securelayer7.net
security application-security ctf ai-safety jailbreak-detection ai-security guardrails prompt-engineering prompt-injection llm-security llm-guardrails ai-firewall prompt-injection-detection
-
Updated
May 31, 2026 - TypeScript
Open-source security platform for AI agents -- audits skills before install, monitors 24/7, shares threat intelligence across all users. | AI Agent 開源安全平台 -- 安裝前審計 skill、24/7 即時監控、社群共享威脅情報。
open-source typescript mcp cybersecurity yara threat-intelligence ai-security threat-detection sigma-rules ai-agent prompt-injection llm-security tool-poisoning
-
Updated
Sep 22, 2026 - TypeScript
Security control plane for AI agents — identity and delegation, capability policy, data-flow taint and a live audit trail, enforced over MCP. Guards a real Claude Code end to end.
mcp ai-agents zero-trust ai-security prompt-injection llm-security model-context-protocol agent-security claude-code
-
Updated
Jul 27, 2026 - TypeScript
Spell whisperer is a prompt injection challenges platform based on Grok API.
-
Updated
May 13, 2026 - TypeScript
A TypeScript library providing a set of guards for LLM (Large Language Model) applications
redaction security typescript defence governance guards hai human-ai guardrails presidio prompt-injection llm-guardrails halucination
-
Updated
Feb 6, 2026 - TypeScript
Metasploit for AI agents: scan, attack, and fix AI agents and MCP servers. Open source security toolkit.
tool mcp penetration-testing security-scanner red-team ai-agents ai-security prompt-injection llm-security agent-security mcp-security
-
Updated
Sep 30, 2026 - TypeScript
Build production ready apps for GPT using Node.js & TypeScript
prompt openai gpt gpt-2 gpt-3 prompt-engineering chatgpt prompt-attack prompt-injection prompt-caching prompt-hardening
-
Updated
May 8, 2023 - TypeScript
Add this topic to your repo
To associate your repository with the prompt-injection topic, visit your repo's landing page and select "manage topics."