Agent Skills

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

Trust Score Usefulness Recommended Stars Latest

Filters

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

GA4 Audit

claude-code-marketing-skills

Run a configuration and data-quality audit of a Google Analytics 4 property: events, streams, custom dimensions, retention, PII, Ads link, and BigQuery export.

analyticsga4audit

6 triggers

Apollo Security Basics

claude-code-plugins-plus-skills

Practical security best-practices for integrating with the Apollo.io API: safe key storage, PII redaction, minimal permissions, rotation, and automated audit ch

securityapiapollo

2,514

5 triggers

Privacy Data-Flow Review

agentic-security

Pre-write privacy review that classifies PII/PHI/PCI, traces where data flows, and generates a DATA_FLOW.md record before code that touches sensitive fields is

privacycompliancepii

7 triggers

AgentWard PII Sanitizer

agentward

Locally redacts PII from text files across 15 categories, ensuring sensitive data never reaches the agent's prompt.

securitypiiprivacy

5 triggers