14 tagged llm-security, measured the same way as everything else here.
Browse within: ai-security 12
Plugin Claude Code
Bundles 2 skills, 1 agent · 379 tokens together
Skeptical-reading and prompt-injection defense for AI coding agents. Trust nothing. Ship safely.
Plugin Claude Code
Bundles 1 command, 1 hook · 18 tokens together
Checks each package the agent is about to install and shows a line for every install, checked or not. Denies packages with malicious indicators and asks you about high-risk ones, look-alike names and anything it could not check (refused in CI).
Plugin Claude Code
safe-plugin. ZIRAN finds the vulnerabilities in AI agents that come from tools combining, not from any single prompt. Graph-based tool chain discovery, execution-level side-effect detection, multi-phase campaigns.
Plugin Claude Code
Local input firewall for AI agents. Scans text and files before an agent reads them. Needs pip install sunglasses first, on Python 3.9 or newer.
Plugin Claude Code
Bundles 1 skill · 160 tokens together
Adversarial, attacker-minded security review of untrusted code before you install it. A read-only scanner plus a five-persona reasoning pass, ending in a GO / GO-WITH-MITIGATIONS / NO-GO verdict.
UnboundCompute/security-agent-skills
Plugin Claude Code
Bundles 194 skills · 32,602 tokens together
Security-testing methodology as portable agent skills, spanning white-box bug hunting, AI-agent and LLM red-teaming, cloud identity and CI/CD trust, client-app trust surfaces across browser and editor extensions and Electron, wire-protocol and token trust across gRPC, WebSocket, and JWT, enterprise identity lifecycle…
Plugin Gemini CLI
A prompt-injection firewall for AI agents, with no AI inside: your agent reads anything and takes orders only from you. For Claude Code, Codex CLI, Kimi Code, DeepSeek Harness, Gemini CLI, MCP hosts and LangChain.
alelaguard/agentguards-plugins
Plugin Claude Code
Bundles 3 skills, 3 hooks · 143 tokens together
LLM security guardrails for Claude Code, for a self-hosted AgentGuards appliance — jailbreak detection, prompt-injection and web-content scanning, data-exfiltration blocking, and destructive-command authorization, enforced entirely by hooks. No bundled MCP server: Claude Code's .mcp.json cannot point at a…
Plugin Claude Code
Bundles 1 skill, 3 commands, 1 hook · 161 tokens together
Grounds your AI coding agent in a cited security baseline (OWASP/CWE/EU AI Act) and warns before risky actions. Advisory, free, read-only. Real-time blocking is Kernora Axiora.
Plugin Claude Code
Bundles 7 skills, 1 MCP server · 310 tokens together
Adversarial co-generation engine — generates code and adversarial attacks from the same spec, concurrently. Adds /gauntlex:run and friends, plus the gauntlex MCP server.
Plugin Cursor
Bundles 3 skills, 3 commands, 1 MCP server · 244 tokens together
Secure enterprise platform for management and implementation of AI agents — Kimss Python SDK, MCP server, and integration guidance for Cursor.
Plugin Claude Code
Bundles 1 skill, 1 MCP server · 419 tokens together
Governed local-LLM observability: model policy, prompt scanner, capture proxy, 21 tools.