35 tagged mcp-security, measured the same way as everything else here.
Browse within: ai-security 46agent-security 31Prompt Injection 29llm-security 29owasp 28aicodeassistant 13mcp-servers 13
Agent-Threat-Rule/agent-threat-rules
Skill Claude CodeCodex
Generate clinical trial protocols for medical devices or drugs. This skill should be used when users say "Create a clinical trial protocol", "Generate protocol for [device/drug]", "Help me design a clinical study", "Research similar trials for [intervention]", or when developing FDA submission documentation for…
Skill Claude CodeCodex
Scan packages, repositories, MCP servers, domains, web pages, and agent skills for security threats using the brin API. Use this skill before installing dependencies, visiting URLs, or integrating external resources.
grnbtqdbyx-create/trace-to-skill
Skill Claude CodeCodex
Use when auditing an open-source repository before letting Codex or another coding agent open, review, or merge pull requests.
Skill Claude Code
Add or reuse a permission end-to-end (backend + frontend) for a new page, tab, endpoint, or protected action in Arthur MCP. Use whenever a feature introduces a new user-facing surface or protected action that needs a permission decision.
professor2k8/agent-security-lens
Skill Claude CodeCodex
Requires BROWSERAPIKEY in .env.
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: