Prompt Injection Defense
Detecting and blocking prompt injection and jailbreaks. As of 2026-11-21, 193 indexed products offer it (58 with full profiles), in 9 forms: 168 MCP servers, 8 Infrastructure, 5 Agent skills, 3 Rules packs. 89 were published in the last 90 days, against 47 in the 90 days before. iFixAi has the most GitHub stars, 54% of the total across 165 products with their own repository.
CapabilitySegment label: Crowded, slowing DER
Available as
All in the directoryProfiled products grouped by product form. Within each form: own-repository products by GitHub stars, then products in a subfolder of a larger repository (they show that repository's stars), up to 10 each.
MCP servers 168 indexed · 36 profiled
Protocol-level reach: 36 of the 45 active platforms AgentSidekick tracks document support for MCP. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | ADRADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber. | uber | 2.1k | 1d ago | ||
| 2 | AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP. | wuyoscar | 2.1k | today | ||
| 3 | HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server. | hashgraph-online | 1.1k | today | ||
| 4 | skylosDead code, security, secrets detection and code quality for Python, TypeScript, Go. | duriantaco | 951 | today | ||
| 5 | VestigeCausal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause. | samvallad33 | 662 | 1d ago | ||
| 6 | agent-opforOpen-source adversary emulation for AI agents and MCP servers. | KeyValueSoftwareSystems | 588 | 18d ago | ||
| 7 | node9Access control for AI agents and MCP servers: allow, hold for approval, or block each tool call | node9-ai | 225 | today | ||
| 8 | www-project-agent-memory-guardRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0. | OWASP | 209 | today | ||
| 9 | shellwardAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP. | jnMetaCode | 140 | 1mo ago | ||
| 10 | agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities. | sinewaveai | 124 | 1mo ago |
Infrastructure 8 indexed · 8 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | iFixAiIndependent Auditing of AI Agents. Run by human or the agent itself, to answer the most crucial question in the AI Agent Economy. Is the agent doing what is supposed to do? With iFixAi you can have this answer in less than 120 seconds. | ifixai-ai | 47k | 1d ago | ||
| 2 | AI-Infra-GuardA full-stack AI Red Teaming platform securing AI ecosystems via Agent Scan, Skills Scan, MCP scan, AI Infra scan and LLM jailbreak evaluation. | Tencent | 7.6k | 1d ago | ||
| 3 | uptrainUpTrain is an open-source unified platform to evaluate and improve Generative AI applications. We provide grades for 20+ preconfigured checks (covering language, code, embedding use-cases), perform root cause analysis on failure cases and give insights on how to resolve them. | uptrain-ai | 2.4k | 2y ago | ||
| 4 | vigil-llm⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs | deadbits | 511 | 2y ago | ||
| 5 | OpenARTOpenART is an open-source framework designed to evaluate the safety and robustness of autonomous AI agents in dynamic, long-horizon, and stateful environments. It stress-tests agent runtimes against multi-step state poisoning, privilege escalation, and tool-use vulnerabilities across 10,000+ benchmark scenarios. | AI45Lab | 277 | 1d ago | ||
| 6 | dodoguardDodoGuard: Take AI Agents to Production. Test, validate, and operate AI Agents before and after deployment.for Dify, Coze, FastGPT, n8n, Tencent ADP, ByteDance HiAgent, and more. | dodoguardai | 275 | 1mo ago | ||
| 7 | ai-runtime-labEngineering deterministic, production-grade systems around non-deterministic LLMs — FSM, durable execution, retries, DAGs, agent runtimes, model routing, edge inference, RAG, memory, multi-agent orchestration, security, and observability. 14 runnable proof-of-concept phases. | Ali-hey-0 | 183 | 4mo ago | ||
| 8 | llm-firewallAI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacks | CollieAi | 47 | 2d ago |
Agent skills 5 indexed · 5 profiled
Protocol-level reach: 26 of the 45 active platforms AgentSidekick tracks document support for the Agent Skills format. DER Which platforms
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | skills-janitorTinder for your Claude Code skills, subagents and MCP servers. Swipe away what wastes context, scan for prompt injection, get honest token costs. Fixes what it finds and actually deletes. Zero dependencies, Claude Code + Codex. | khendzel | 139 | 1mo ago | ||
| 2 | nemo-guardrailsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU. | Orchestra-Research | — | 1mo ago | ||
| 3 | prompt-guardMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security. | Orchestra-Research | — | 1mo ago | ||
| 4 | hunt-llm-aiHunt LLM/AI feature bugs — prompt injection, indirect injection, exfiltration via tool-use/markdown, ASCII smuggling, agentic AI security (OWASP Agentic Apps 2026, ASI01-ASI10). Patterns: direct injection ('ignore previous instructions'), indirect injection via documents/web pages/email the model reads, ASCII smuggling (Unicode Tags block U+E0000-U+E007F, invisible to humans, decoded by the model), tool-use exfiltration (model has fetch/browse tool, attacker injects OOB URL, model exfils chat history/secrets), markdown-image zero-click exfil, system-prompt extraction, IDOR-via-AI (cross-tenant data). Targets: chatbots, RAG, summarizers, agentic copilots, MCP tools. Detection: any LLM-backed endpoint, doc upload triggering AI processing, autonomous agent with tools. Validate: OOB/Collaborator callback for exfil, verbatim-reproducible system-prompt leak (run twice), verifiable cross-tenant leak or RCE. Confabulation is NOT a finding. Use when hunting AI features, chatbots, RAG, agentic systems, MCP. | elementalsouls | — | today | ||
| 5 | hunt-rag-vectorHunt vector-store / embedding-layer weaknesses in RAG pipelines (OWASP LLM08 Vector and Embedding Weaknesses) — persistent corpus poisoning that survives across sessions and users (distinct from one-shot indirect prompt injection, which is owned by hunt-llm-ai), cross-tenant vector-database IDOR (unauthenticated or unscoped queries against Pinecone/Weaviate/Chroma/Milvus/Qdrant/pgvector), source-text/metadata leakage in similarity-search results, and retrieval-hijack via adversarial embedding proximity ('SEO poisoning' for RAG). Targets: any app with a shared knowledge base, document upload feeding a chatbot, or a directly reachable vector-DB port. Validate: a second, clean session/account must inherit a poisoned result, or a cross-tenant artifact must be independently verifiable — confabulation is not a finding, same bar as hunt-llm-ai. Use when target is RAG-backed, exposes a vector-DB port, or lets users upload documents that other users' queries later retrieve. | elementalsouls | — | today |
Rules packs 3 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | artguardOpen-source AI artifact scanner. Detect malicious agent skills, MCP servers, and IDE rule files before they run. | spiffy-oss | 32 | 8mo ago |
Developer tools 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity. | NVIDIA | 10k | 3d ago | ||
| 2 | Snyk Agent ScanScanner that inspects installed MCP servers and agent configs for tool poisoning, prompt injection and toxic flows. | Snyk (Invariant Labs) | 3.3k | 2d ago |
Frameworks 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | AutoHarnessAutoHarness: Automated Harness Engineering for AI Agents | aiming-lab | 470 | 7mo ago | ||
| 2 | syadagenticUniversal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified. | Sekolah76 | 110 | 2mo ago |
Libraries 2 indexed · 2 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | GiskardTesting library that scans LLM agents and RAG apps for hallucination, prompt injection and harmful-content vulnerabilities and generates test suites. | Giskard | 6.0k | 1d ago | ||
| 2 | ai-safe2-frameworkGovernance, risk, compliance and security for agentic AI, non-human identities and swarms. A Rosetta Stone connecting threats, standards, controls and evidence, with AISM maturity assessment, NEXUS runtime governance and tools to build, assess and defend AI systems. | CyberStrategyInstitute | 159 | 1d ago |
Plugins 2 indexed · 1 profiled
1 of these are Claude plugins, which Claude Code documents (protocol-level). DER
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | hardstopDon't let AI destroy your hard work! HardStop is a rock-solid protection for AI-generated commands. Pre-execution safety validation for Claude Code, Claude Cowork. Catches dangerous commands before they run: whether from AI mistakes, hallucinations, prompt injection, or misunderstood instructions. Seatbelts for the agentic AI era. | frmoretto | 32 | 7mo ago |
AI APIs 1 indexed · 1 profiled
No compatibility evidence is collected for this form.
| # | Product | Publisher | Capabilities | GitHub stars | Last push | Save and compare |
|---|---|---|---|---|---|---|
| 1 | Lakera GuardAPI that screens LLM inputs and outputs for prompt injection, data leakage and harmful content in real time. | Check Point (Lakera) | — | — |
Which platforms these forms can reach
All platformsProtocol-level: the platform documents support for the standard. No specific pairing has been tested.
MCP servers 168 indexed here
36 platforms document MCP support CUR.
ContinueOpenCodeClaude CodeCodexGemini CLIZedOpenHandsClineWarpgooseQwen CodeBolt (bolt.new)KiroAmazon Bedrock AgentCoreAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)Augment CodeChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)Gemini Enterprise Agent Platform (formerly Vertex AI / Vertex AI Agent Builder)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJetBrains AI AssistantJunieLovableMicrosoft Copilot StudioReplit AgentTabninev0
Agent skills 5 indexed here
26 platforms document Agent Skills support CUR.
OpenClawOpenCodeClaude CodeCodexGemini CLIOpenHandsWarpgooseBolt (bolt.new)KiroAmpApps in ChatGPT / Apps SDK (now ChatGPT Plugins)ChatGPTClaude (claude.ai apps)Claude DesktopCursorDevinDevin Desktop (formerly Windsurf)Factory (Droid)Gemini (app)GitHub CopilotGitHub Copilot cloud agent (formerly Copilot coding agent)Google AntigravityJunieReplit AgentTabnine
Platforms publishers name
| Platform | Profiled products naming it |
|---|---|
| Claude Code | 2 |
| Codex | 2 |
| OpenCode | 1 |
Integrations most often paired
Third-party services named by products with this capability, whole catalogue.
| Integration | Products | Share |
|---|---|---|
| GitHub | 4 | 2.1% |
| Gmail | 3 | 1.6% |
| PostgreSQL | 2 | 1.0% |
| AWS | 1 | 0.5% |
| Azure | 1 | 0.5% |
| Google Cloud | 1 | 0.5% |
| Kubernetes | 1 | 0.5% |
| Obsidian | 1 | 0.5% |
| Outlook | 1 | 0.5% |
| Pinecone | 1 | 0.5% |
| Qdrant | 1 | 0.5% |
| Slack | 1 | 0.5% |
Keywords that trigger this capability
Matched as whole words, ignoring case, in a product's name, description and repository topics.
| Keyword | Products matched |
|---|---|
| prompt injection | 182 |
| jailbreak detection | 3 |
| injection detection | 4 |
| indirect prompt injection | 4 |
| llm firewall | 0 |
Segment statistics
Whole catalogue (193 indexed products). Calculated 2026-11-21.
Crowded, slowing. Among the largest fifth of capabilities, but its launches grew more slowly than the catalogue’s. Size is ranked against all capabilities; momentum compares launches in the last 90 days with the 90 before, relative to the catalogue’s own ratio (62 or more = faster, 38 or less = slower; under 5 dated launches it is not measured). The HHI of 0.316 means stars are spread as if across about 3 equally popular projects — highly concentrated by the common 0.15 / 0.25 thresholds. Stars measure attention, not usage or quality.
Limits
- Classification is by the keywords above. A product that offers this capability without using one of them is not counted; one that uses a keyword in another sense is counted wrongly. Methodology
- Platform reach is protocol-level: it says a platform documents the standard, not that any product here was tested on it. Platforms named by publishers are their own claims.
- Stars belong to repositories. Products in a subfolder of a large repository show that whole repository’s stars and are excluded from the concentration figures.
- Launch counts use each source’s publication date; for auto-discovered repositories that is the repository’s creation date.
Page data last updated .