Agent Skills

Agent Skill Trust Check

marketplace

Static pre-install security and provenance scanner for SKILL.md packages and marketplace listings.

Command Injection Detection

claude-skill-registry

Detect unsafe OS command execution patterns (system/popen/exec) and trace user-controlled input to identify command injection risks.

step-ca (Smallstep)

TerminalSkills Skills Library

Run a private certificate authority to issue and manage internal TLS certificates and mTLS.

Repository Security Posture

superagent-ai

Audit a GitHub repository's security posture and produce a ranked, actionable hardening checklist.

Pentesting FreeIPA — LDAP & Kerberos attack paths

xalgorix

Offensive/blue-team skill for authorized pentests: enumerates FreeIPA/LDAP/Kerberos environments, finds HBAC/sudo misconfigurations, reuses CCACHE/keytabs and m

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

/credteam — Red Team Assessment

correctless

Goal-directed red team assessment skill for live systems with source-code access; enforces isolation and intensity gating before active testing.

Config Hardener

openclaw-skills-security

Audit an OpenClaw installation and generate a prioritized, ready-to-apply hardening plan for AGENTS.md, gateway, sandbox, and permissions.

AI/ML Workflow Bundle

agent-skills-library

A comprehensive workflow bundle for designing, building, and operating LLM applications, RAG systems, AI agents, and ML pipelines.

Code Reviewer — Constructive PR Reviews

skills-for-antigravity

Performs high-value code reviews focused on correctness, security, and developer growth; prioritises substantive issues over bikeshedding and uses repo referenc

Deception-Based Detection with Canarytoken

xalgorix

Create, deploy, and monitor Thinkst Canary Tokens (web, DNS, document, AWS key) to detect lateral movement and credential misuse.

Azure Key Vault Certificates SDK (Rust)

antigravity-awesome-skills

Client library usage guide for Azure Key Vault Certificates in Rust — create, import, manage, and list certificates.

PHP (Modern Practices)

agentguard

Guidelines and best practices for modern PHP (8.4–8.5): typing, security, architecture, testing, and performance for writing and reviewing PHP code.

ERC4626 Vault Patterns

vigilo

Audit-oriented patterns and mitigations for ERC4626 tokenized vaults: share/asset conversions, inflation (first-depositor) defenses, rounding rules, donation at

Delete API Key (LiteLLM)

litellm-skills

Remove one or more API keys or key aliases from a LiteLLM proxy after confirming with the user; calls POST /key/delete and returns the deleted_keys list.

AI Pentesting

TerminalSkills Skills Library

Automate penetration testing workflows by orchestrating security tools (nmap, subfinder, nuclei, sqlmap) with AI agents to find, prove, and report web applicati

SARIF Parsing Expert

prodsec-skills

Analyzes, filters, and aggregates SARIF files from static analysis tools like CodeQL and Semgrep.

CC Proxy Detector

zxc123aa

Detects the real backend origin of Claude Code proxy services.

Stinking Cloud (Area Denial)

wizards-of-the-ghosts

Implement defensive area-denial mechanisms like rate limiting, tarpits, and honeypots to deter unwanted traffic.

Docker Patterns for Python

claude-code-python-stack

Implements industry-standard Docker and Docker Compose patterns for Python, Django, and FastAPI projects, focusing on multi-stage builds and security.

Python Security Analysis & Remediation

Python Refactoring Skills

Detect and fix security vulnerabilities in Python code, including SQL injection, hardcoded secrets, and weak cryptography using Bandit and Ruff.

Shannon AI Pentester

Keygraph Shannon

Autonomous AI-driven pentesting tool for web apps and APIs. Performs real exploits to prove vulnerabilities with high success rates.

Sam's Architecture Standards

claude-skills

A comprehensive set of architectural standards and anti-patterns for Python APIs, DevOps, and embedded systems to ensure scalability and security.

Vibe Security Auditor

vibe-security-skill

Audits AI-generated codebases for critical security flaws like exposed keys, broken RLS, and insecure payment flows.

Idiomatic Go 1.25 Development Guide

agentguard

Expert guidance on Go 1.25 practices, covering concurrency, error handling, generics, and security hardening.

Binary Ninja CLI

bn

Perform advanced reverse engineering tasks using the local bn CLI against an open Binary Ninja session.

Database Workflow Specialist

rune

Automates database migrations with safety checks, breaking change detection, and SQL injection scanning for multiple ORMs.

HardStop Command Safety

hardstop

A safety layer that blocks dangerous shell commands and warns on risky system operations to prevent accidental damage.

Security Headers Compliance

trezor-suite

Ensures generated code aligns with security headers and permissions policies, specifically for navigator object interactions.

CTF — Binary Exploitation (Pwn)

ctf-super-hub

A comprehensive quick-reference skill for CTF binary exploitation: buffer overflows, format strings, heap techniques, ROP, ret2libc, shellcode, kernel exploits