AgentSidekick

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 directory

Profiled 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

Prompt Injection Defense: MCP servers by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1ADRADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.uber2.1k1d ago
2AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.wuyoscar2.1ktoday
3HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.hashgraph-online1.1ktoday
4skylosDead code, security, secrets detection and code quality for Python, TypeScript, Go.duriantaco951today
5VestigeCausal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.samvallad336621d ago
6agent-opforOpen-source adversary emulation for AI agents and MCP servers. KeyValueSoftwareSystems58818d ago
7node9Access control for AI agents and MCP servers: allow, hold for approval, or block each tool callnode9-ai225today
8www-project-agent-memory-guardRuntime defense against memory poisoning in AI agents (OWASP ASI06). Drop-in for LangChain, OpenAI Agents, AutoGen, CrewAI and mem0.OWASP209today
9shellwardAI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.jnMetaCode1401mo ago
10agent-security-scanner-mcpSecurity layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.sinewaveai1241mo ago

All 36 profiled MCP servers with this capability

Infrastructure 8 indexed · 8 profiled

No compatibility evidence is collected for this form.

Prompt Injection Defense: Infrastructure by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1iFixAiIndependent 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-ai47k1d ago
2AI-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.Tencent7.6k1d ago
3uptrainUpTrain 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-ai2.4k2y ago
4vigil-llm⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputsdeadbits5112y ago
5OpenARTOpenART 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.AI45Lab2771d ago
6dodoguardDodoGuard: 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. dodoguardai2751mo ago
7ai-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-01834mo ago
8llm-firewallAI Firewall & LLM security toolkit - protect your AI applications from prompt injection, jailbreaks, PII leakage, and adversarial attacksCollieAi472d 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

Prompt Injection Defense: Agent skills by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1skills-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.khendzel1391mo ago
2nemo-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
3prompt-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
4hunt-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
5hunt-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.

Prompt Injection Defense: Rules packs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1artguardOpen-source AI artifact scanner. Detect malicious agent skills, MCP servers, and IDE rule files before they run.spiffy-oss328mo ago

Developer tools 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Prompt Injection Defense: Developer tools by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity.NVIDIA10k3d ago
2Snyk Agent ScanScanner that inspects installed MCP servers and agent configs for tool poisoning, prompt injection and toxic flows.Snyk (Invariant Labs)3.3k2d ago

Frameworks 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Prompt Injection Defense: Frameworks by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1AutoHarnessAutoHarness: Automated Harness Engineering for AI Agentsaiming-lab4707mo ago
2syadagenticUniversal Zero-Refusal Agent Framework - 40+ jailbreak templates (T1-T119), 1128 curated skills, executable framework-core, installer untuk Hermes/Claude/Codex/opencode. Verified.Sekolah761102mo ago

Libraries 2 indexed · 2 profiled

No compatibility evidence is collected for this form.

Prompt Injection Defense: Libraries by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1GiskardTesting library that scans LLM agents and RAG apps for hallucination, prompt injection and harmful-content vulnerabilities and generates test suites.Giskard6.0k1d ago
2ai-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.CyberStrategyInstitute1591d ago

Plugins 2 indexed · 1 profiled

1 of these are Claude plugins, which Claude Code documents (protocol-level). DER

Prompt Injection Defense: Plugins by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1hardstopDon'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.frmoretto327mo ago

AI APIs 1 indexed · 1 profiled

No compatibility evidence is collected for this form.

Prompt Injection Defense: AI APIs by GitHub stars
#ProductPublisherCapabilities GitHub stars Last push Save and compare
1Lakera 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 platforms

Protocol-level: the platform documents support for the standard. No specific pairing has been tested.

Platforms publishers name

PlatformProfiled products naming it
Claude Code2
Codex2
OpenCode1

Integrations most often paired

Third-party services named by products with this capability, whole catalogue.

IntegrationProducts Share
GitHub42.1%
Gmail31.6%
PostgreSQL21.0%
AWS10.5%
Azure10.5%
Google Cloud10.5%
Kubernetes10.5%
Obsidian10.5%
Outlook10.5%
Pinecone10.5%
Qdrant10.5%
Slack10.5%

Keywords that trigger this capability

Matched as whole words, ignoring case, in a product's name, description and repository topics.

KeywordProducts matched
prompt injection182
jailbreak detection3
injection detection4
indirect prompt injection4
llm firewall0

Segment statistics

Whole catalogue (193 indexed products). Calculated 2026-11-21.

193DERIndexed products58 with full profiles
89DERLaunched, last 90 days47 in the 90 days before
26DERMomentum vs catalogue50 = same pace as the catalogue
54%DERLargest project's share of starsAcross 165 products with their own repository
0.316DERConcentration (HHI)About 3 equal-sized projects’ worth; highly concentrated
2SRCMedian starsPer product with its own repository
79%DEROpen sourceMarked open source; unknown counts as not

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 .