Agent Skills

SKILL.md packages that extend Claude Code, Cursor, Copilot, and other AI agents.

Trust Score Usefulness Recommended Stars Latest

Filters

Anthropic Security Basics

skillshub

Practical security practices for Anthropic Claude integrations: API key management, input validation, prompt-injection defenses, and output scanning.

securityanthropicclaude

6 triggers

Bagman — Secure Key Management

openclaw-master-skills

Secure key-management patterns and operational guardrails for AI agents that need to handle private keys, session keys, and secrets safely.

securitysecretskeys

1,990

7 triggers

ClawMoat — Agent Security Scanner

clawmoat

Scans agent inputs and outputs for prompt injection, jailbreaks, credential leaks, PII, and unsafe tool calls; includes scripts for scanning and auditing.

securityagent-securityprompt-injection

5 triggers

Skill Vetter

skill-vetter

Pre-install security gate that scans a skill for prompt-injection, secrets, and other vulnerabilities before installation.

securityscanningsupply-chain

5 triggers

API Relay Security Audit

api-relay-audit

An 11-step automated security audit for AI API relay/proxy services — detects prompt injection, context truncation, tool-call substitution, stream integrity iss

securityauditrelay

427

5 triggers