security MCP Server
ESLint security rules for MCP servers — catches SANDWORM_MODE credential harvesting, path traversal, command injection, and CVE patterns at dev time
Discovered via github-topic:mcp and last synced 3mo ago.
1. Install the package
npm install eslint-plugin-mcp-security
Catches
`eval()`, `new Function()`, `vm` module in tool handlers
CVSS
Multiple `.tool()` calls with the same name — silent overwrites
`no-duplicate-tool-names`, `no-credential-paths-in-descriptions`, `no-dynamic-tool-registration`
Handler accessing parameters without an input schema
`.tool()` calls missing a Zod schema argument
McpServer instance shared across requests (CVE-2026-25536)
Rules
What it catches
`process.env` or credential file reads returned in tool results
`exec`, `execSync`, `spawn` with user input in tool handlers
`process.exit()`, recursive delete in handlers
Tool descriptions referencing `~/.ssh`, `~/.aws`, `.env` — SANDWORM_MODE pattern
Non-literal tool names or descriptions — runtime injection risk
`require-auth-check-in-handler`
Filesystem operations without path boundary validation
Handlers with no auth/verify/session check
API keys, tokens, connection strings in source code
真实性验证技能。分析用户提供的信息、消息、图片或内容，判断其真实性和可信度，识别虚假信息、AI生成内容或伪造内容。
Container escape is a critical attack technique where an adversary breaks out of container isolation to access the host system or other containers. Detection involves monitoring for escape indicators
Pod Security Standards (PSS) define three levels of security policies -- Privileged, Baseline, and Restricted -- enforced by the Pod Security Admission (PSA) controller built into Kubernetes 1.25+. PS
Implements eBPF-based security monitoring using Cilium Tetragon for real-time process execution tracking, network connection observability, file access auditing, and runtime enforcement. Covers TracingPolicy CRD authoring with kprobe/tracepoint hooks, in-kernel filtering via matchArgs/matchBinaries selectors, JSON event export, and integration with SIEM pipelines. Use when building kernel-level runtime security observability for Linux hosts or Kubernetes clusters.
AI Agent Governance Toolkit — Policy enforcement, zero-trust identity, execution sandboxing, and reliability engineering for autonomous AI agents. Covers 10/10 OWASP Agentic Top 10.
Open-source sandboxed agent harness for teams. Giving every employee a secured personal agent.
AI agent security scanner. Detect vulnerabilities in agent configurations, MCP servers, and tool permissions. Available as CLI, GitHub Action, ECC plugin, and GitHub App integration. 🛡️
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Learn how to use the absolute-audit Claude skill. Complete guide with installation instructions and examples.
Learn how to use the token-scam-analysis Claude skill. Complete guide with installation instructions and examples.
Learn how to use the absolute-upgrade Claude skill. Complete guide with installation instructions and examples.