AgentSidekick

Agent Threat Protection

Defending agents from injection, poisoned tools and leaks. As of 2026-11-21, 473 indexed products match this subcategory (138 with full profiles); 213 were published in the last 90 days, against 115 in the 90 days before, slower than the catalogue as a whole. By GitHub stars, iFixAi leads, holding 24% of the stars of the 398 products here with their own repository. The most common form is MCP servers (90% of indexed products).

SubcategorySegment label: Lagging the catalogue DER

Segment statistics

Whole catalogue (all 473 indexed products, not only profiled ones). Calculated 2026-11-21.

473DERIndexed products138 with full profiles
213DERLaunched, last 90 days115 in the 90 days before
26DERMomentum vs catalogue50 = same pace as the catalogue
24%DERLargest project's share of starsAcross 398 products with their own repository
0.103DERConcentration (HHI)About 10 equal-sized projects’ worth; unconcentrated
2SRCMedian starsPer product with its own repository
76%DEROpen sourceMarked open source; unknown counts as not

Lagging the catalogue. Mid-sized for its level, with launches growing more slowly than the catalogue’s. Size is ranked against the other subcategory nodes; momentum compares this node’s launches in the last 90 days with the 90 before, relative to the whole catalogue’s ratio (score 62 or more = faster, 38 or less = slower; below 5 dated launches it is not measured and the label uses size alone).

Concentration. The Herfindahl–Hirschman index (HHI) adds up each project’s squared share of stars. At 0.103, attention is spread as if across about 10 equally popular projects. Using the common competition-policy thresholds (0.15 and 0.25), that is unconcentrated. Stars measure attention, not usage or quality.

Which product forms serve it

The same need is met by MCP servers, agent skills, plugins, extensions and frameworks. This counts each form across the whole catalogue.

Products in Agent Threat Protection by product type, as of 2026-11-21
Product type IndexedShareWith a profile
MCP servers42489.6%93
Infrastructure143.0%14
Agent skills112.3%11
Plugins71.5%5
Libraries61.3%6
Rules packs30.63%1
Frameworks30.63%3
Developer tools20.42%2
Agent projects20.42%2
AI APIs10.21%1

4 capabilities

Indexed = whole catalogue; profiled = products with their own page. A product can sit in several, so the rows do not add up to the total.

CapabilityIndexed ProfiledNew, 90 daysLabel
Prompt Injection DefenseDetecting and blocking prompt injection and jailbreaks.1935889Crowded, slowing
Data Loss PreventionDetecting and redacting sensitive data.892044Lagging the catalogue
Secrets ManagementStoring and injecting credentials safely.571426Lagging the catalogue
MCP Server ScanningAuditing MCP servers for malicious or risky tools.471322Lagging the catalogue

Top 40 products by GitHub stars

Search the directory

Profiled products only (138 of 473), ranked by the stars of their own repository. Products that live in a subfolder of a larger repository (common for skills) show that whole repository's stars and are ranked after them; products without a repository come last. Stars are popularity, not quality or installs.

Agent Threat Protection: top profiled products by GitHub stars, 2026-11-21
#ProductTypePublisherCapabilities GitHub stars Last push LicenceSave 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.Infrastructureifixai-ai47k1d agoApache-2.0
2infisicalInfisical is the open-source platform for securing secrets, certificates, access, and AI Agents.Agent projectInfisical31ktoday—
3mcp-for-beginnersThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable, and secure AI workflows from session setup to service orchestration.MCP servermicrosoft18ktodayMIT
4OmniGetDesktop toolbox for coding agents: downloads, files, pages, ports, chats and cleanup, in OmniGetMCP servertonhowtf15k1d agoGPL-3.0
5garakLLM vulnerability scanner that probes models and apps for jailbreaks, prompt injection, data leakage and toxicity.Developer toolNVIDIA10k3d agoApache-2.0
6AI-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.InfrastructureTencent7.6k1d agoApache-2.0
7NeMo GuardrailsToolkit for adding programmable rails (topic control, jailbreak and content safety checks) to LLM apps using the Colang language.LibraryNVIDIA7.5k2d agoApache-2.0
8bla🛡️ BLA (bla-agents / Blind LLM Agents) — Open-source Blue Defense MCP server & CLI protecting JS/TS, Electron ASAR, WASM, Python, Native Binaries, SQLite, GGUF/Safetensors & Android DEX against AI reverse-engineering agents (REA).MCP serverqybaihe6.4ktodayMIT
9GiskardTesting library that scans LLM agents and RAG apps for hallucination, prompt injection and harmful-content vulnerabilities and generates test suites.LibraryGiskard6.0k1d agoApache-2.0
10Handsy AILet AI agents see and operate a real iPhone via an ESP32-S3 USB HID + AirPlay. No jailbreak.MCP serveronehumanbeing5.2ktodayMIT
11nonoagent runtime security - zero trust, zero setup, zero latency agent sandboxingAgent projectnolabs-ai5.1k1d agoApache-2.0
12AI-Engineer-HeadquartersA collection of scientific methods, processes, algorithms, and systems to build stories & models.Infrastructurehemansnation3.8k24d ago—
13Snyk Agent ScanScanner that inspects installed MCP servers and agent configs for tool poisoning, prompt injection and toxic flows.Developer toolSnyk (Invariant Labs)3.3k2d agoApache-2.0
14bionic-gptBionic is sovereign Agentic AI for the enterprise — Runs on-premise and can securely work with your sensitive data and systems.Infrastructurebionic-gpt2.4k4d agoApache-2.0
15uptrainUpTrain 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.Infrastructureuptrain-ai2.4k2y agoApache-2.0
16toolhiveToolHive is an enterprise-grade platform for running and managing Model Context Protocol (MCP) servers.MCP serverstacklok2.3ktodayApache-2.0
17ADRADR secures enterprise AI agents through observability, security benchmarking, and threat detection. Deployed at Uber.MCP serveruber2.1k1d agoApache-2.0
18AISafetyHotAI Safety HOT: daily AI safety news, papers and incidents in one place — jailbreaks, prompt injection, alignment, evals, governance. Website, daily digest, RSS and MCP.MCP serverwuyoscar2.1ktoday—
19agentic_securityAgentic LLM Vulnerability Scanner / AI red teaming kit 🧪Frameworkmsoedov2.0k2d agoApache-2.0
20Docker MCP GatewayGateway that runs MCP servers in isolated containers and exposes them through one endpoint, with secrets management and call interception.InfrastructureDocker1.6k2d agoMIT
21FuzzyAIA powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jailbreaks in their LLM APIs.Infrastructurecyberark1.6k9mo agoApache-2.0
22HOL GuardLocal-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.MCP serverhashgraph-online1.1ktodayApache-2.0
23agentic-radarA security scanner for your LLM agentic workflowsMCP serversplx-ai1.1k8d agoApache-2.0
24skylosDead code, security, secrets detection and code quality for Python, TypeScript, Go.MCP serverduriantaco951todayApache-2.0
25ThinkWatchSelf-hosted AI API and MCP gateway for organizations: SSO and RBAC, per-user identity for MCP tool calls, PII redaction and tool-call guards, rate limits, budgets, cost accounting and audit logs.InfrastructureThinkWatchProject817today—
26AnythingMCPMCP gateway and company brain: 957 connectors (SAP, ERP, SQL), file search, memory and skills.MCP serverHelpCode-ai815todayAGPL-3.0
27Tracekit MCP gatewayMCP gateway you deploy: a Tracekit signer decides and signs each call; agents send each run's token.MCP serverCygnux-Labs760todayMIT
28VestigeCausal Proof Engine for AI agents: signed log, zero vectors, failures traced to their cause.MCP serversamvallad336621d agoAGPL-3.0
29Claude-Code-CyberSecurity-Skill22 production-quality Claude Code Skills for cybersecurity professionals , covering offensive security, defensive operations, reverse engineering, threat hunting, threat intelligence, purple team / adversary emulation, CSOC automation, AI/LLM security, mobile, OT/ICS, GRC, software supply chain security, and more. Agent skillMasriyan5911mo ago—
30agent-opforOpen-source adversary emulation for AI agents and MCP servers. MCP serverKeyValueSoftwareSystems58818d ago—
31Emilia ProtocolExact-action approval for consequential agent actions: request, track, and verify signed receipts.MCP serveremiliaprotocol5255d agoApache-2.0
32blitzstrikeBlitz Strike — a universal MCP security-audit toolbelt. Reconnaissance at speed. Analysis in depth. Validation before report.MCP servershinthink52317d agoMIT
33vigil-llm⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputsInfrastructuredeadbits5112y agoApache-2.0
34lunarlunar.dev: Agent native MCP Gateway for governance and securityMCP serverTheLunarCompany509todayMIT
35AutoHarnessAutoHarness: Automated Harness Engineering for AI AgentsFrameworkaiming-lab4707mo agoMIT
36AgentHoundOffensive security framework for AI agent infrastructure - recon, credential looting, model exfiltration, poisoning, and attack-path analysis across MCP, A2A, gateways, and AI services. BloodHound for the agentic stack.MCP serveradithyan-ak4668d agoApache-2.0
37outputaiOutput.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality reviewer), 40+ slash-command skills covering scaffolding, debugging, evaluation, and credential management, plus a SessionStart hook that auto-loads Output SDK conventions so Claude understands the framework before the first prompt.Plugingrowthxai445todayApache-2.0
38mcp-gatewayA plugin-based gateway that orchestrates other MCPs and allows developers to build upon it enterprise-grade agents.MCP serverlasso-security40310mo agoMIT
39claude-code-organizerOrganize Claude Code memories, skills, MCP servers, commands, agents, rules via drag-and-drop.MCP servermcpware395todayMIT
40cross-code-organizerCross-Code Organizer (formerly Claude Code Organizer): cross-harness config dashboard for Claude Code, Codex CLI, MCP servers, skills, memories, agents, sessions, security scanning, context budget, and backups.MCP servermcpware395todayMIT

Most common integrations

Third-party services named by products in this node, whole catalogue.

IntegrationProducts Share
GitHub51.1%
PostgreSQL51.1%
YouTube40.8%
Gmail30.6%
MySQL30.6%
AWS20.4%
Android20.4%
Google Cloud20.4%
Slack20.4%
Azure10.2%
Google Drive10.2%
GraphQL10.2%
Kubernetes10.2%
Obsidian10.2%
Outlook10.2%

Launches per month

New Agent Threat Protection products per monthSRC

Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.

New Agent Threat Protection products per monthWhole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.. Products published: 20 points, latest 68 products in 2026-11.
Show the data as a table
New Agent Threat Protection products per month. Whole catalogue, by publication month, 2024-12 to 2026-11. The last month is partial; undated products are excluded.
Products published (products)
2024-122
2025-021
2025-032
2025-043
2025-051
2025-061
2025-102
2025-114
2025-121
2026-017
2026-0218
2026-0324
2026-0432
2026-0528
2026-0629
2026-0743
2026-0843
2026-0952
2026-1083
2026-1168

Related opportunities

Opportunity radar

Scored gaps for this node or anything beneath it. Scores rank hypotheses; they do not predict demand.

No scored opportunity here

Capability gaps are only scored inside subcategories with at least 20 indexed products, and only the top 80 are kept. None falls under this node.

Limits of these numbers

  • Products are placed here by whole-word keyword rules on their name, description and repository topics, and inherit every ancestor of a matched node. Products that do this without naming it are missed; ambiguous words cause false matches. Methodology
  • About half of the catalogue matches no node at all, so absolute counts understate every category.
  • Launch counts use the publication date each source reports; for auto-discovered repositories that is the repository’s creation date.
  • Stars and concentration cover only products with their own repository (not a subfolder of a larger one). They measure attention, not adoption.

Page data last updated .