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
Apr 11, 2026 - TypeScript
#
prompt-injection
Here are 1,855 public repositories matching this topic...
A full-stack AI Red Teaming platform securing AI ecosystems via OpenClaw Security Scan, Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation.
agent security scanner vulnerability security-tools ai-security ai-infra mcp-scan llm prompt-injection llm-security llm-evaluation prompt-security agent-security ai-red-teaming openclaw-security skill-scanner llm-jailbreak skills-security
-
Updated
Jun 12, 2026 - Python
The Security Toolkit for LLM Interactions
transformers security-tools adversarial-machine-learning large-language-models llm prompt-engineering chatgpt llmops prompt-injection llm-security
-
Updated
Dec 15, 2025 - Python
AI Red Teaming playground labs to run AI Red Teaming trainings including infrastructure.
-
Updated
Feb 13, 2026 - TypeScript
A playground of highly experimental prompts, Jinja2 templates & scripts for machine intelligence models from OpenAI, Anthropic, DeepSeek, Meta, Mistral, Google, xAI & others. Alex Bilzerian (2022-2025).
prompt text-analysis prompt-toolkit jinja jinja2-templates ai-agents multimodal rag prompt-learning prompt-tuning prompt-engineering prompting prompt-generator promptengineering prompt-injection prompt-management prompt-template meta-prompting
-
Updated
Jul 12, 2025 - Jinja
LLM Prompt Injection Detector
-
Updated
Aug 7, 2024 - TypeScript
a security scanner for custom LLM applications
-
Updated
Dec 1, 2025 - Python
🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀
-
Updated
Nov 22, 2024 - Jupyter Notebook
💼 another CV template for your job application, yet powered by Typst and more
-
Updated
May 30, 2026 - Typst
Open-source AI agent firewall for MCP security and agent egress. Scans mediated HTTP, MCP, A2A, and WebSocket traffic for exfiltration, SSRF, and prompt injection, and emits mediator-signed action receipts: verifiable audit evidence from outside the agent.
golang security mcp dlp ssrf security-tools ai-agents integrity-monitoring ai-security security-scanning github-action prompt-injection llm-security fetch-proxy agent-security mcp-security ai-firewall ai-agent-security egress-proxy ssrf-protection
-
Updated
Jun 15, 2026 - Go
Every practical and proposed defense against prompt injection.
-
Updated
Feb 22, 2025
Local security audit for AI API relays and LLM proxies: detects prompt injection, model substitution, tool-call rewriting, SSE anomalies, error leakage, and Web3 wallet risks.
python cli security-audit api-gateway security-scanner ai-agents claude ai-security supply-chain-security openai-api web3-wallet prompt-injection anthropic llm-security llm-proxy web3-security ai-audit llm-audit model-substitution tool-call-rewriting
-
Updated
Jun 12, 2026 - Python
Arcjet JavaScript (JS) / TypeScript SDK. Stop bots and automated attacks from burning your AI budget, leaking data, or misusing tools with Arcjet's AI security building blocks.
nodejs javascript security typescript serverless nextjs webassembly rate-limiting javascript-library typescript-library developer-tools remix security-tools bun sveltekit prompt-injection prompt-injection-defense
-
Updated
Jun 15, 2026 - TypeScript
A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents.
-
Updated
Jun 2, 2026 - Python
⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs
security-tools adversarial-machine-learning adversarial-attacks yara-scanner large-language-models llmops prompt-injection llm-security
-
Updated
Jan 31, 2024 - Python
Catch your AI's mistakes and blind spots before your customers or regulators do. iFixAi runs 45 inspections, 32 graded core plus 13 extended for frontier risks like sabotage, sandbagging, and oversight evasion. It returns a letter grade in under 5 minutes. Industry and model agnostic.
python cli ai risk-assessment ai-safety risk-management diagnostic-tool ai-alignment responsible-ai ai-evaluation ai-governance prompt-injection llm-security llm-evaluation hallucination-detection eu-ai-act agent-evaluation owasp-llm nist-ai-rmf iso-42001
-
Updated
Jun 13, 2026 - Python
Deterministic safety solutions for probabilistic AI agents
open-source mcp self-hosted deterministic policy-engine ai-agents ai-security guardrails runtime-safety prompt-injection agentic-ai agent-skills agent-security agent-runtime agent-safety agent-harness intent-verification agent-guardrails openclaw openclaw-skills
-
Updated
Jun 15, 2026 - Python
This repository provides a benchmark for prompt injection attacks and defenses in LLMs
-
Updated
Oct 29, 2025 - Python
Open source local-first PR scanner that finds dead code, security bugs, secrets, quality regressions, and AI-code mistakes before merge. For first timers refer to https://duriantaco.github.io/skylos/repo-map/
javascript python java go dart php typescript static-analysis code-quality python-security devsecops ai-agents code-scanning sast github-actions dead-code prompt-injection ai-generated-code ai-code-review dead-code-detection
-
Updated
Jun 15, 2026 - Python
Improve this page
Add a description, image, and links to the prompt-injection topic page so that developers can more easily learn about it.
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."