Security & Testing Agent Skills for Claude Code

This skill enables Claude to orchestrate complex test workflows using the test-orchestrator plugin.

Enrolls a project in OSS-Fuzz, Google's free continuous fuzzing service for open source, and drives it locally.

Evaluate execution with three-stage verification pipeline

Patches past the barriers that stop a fuzzer making progress — checksum and hash verification, magic-value validation, time-based seeds…

Automates software development overnight using Git hooks to enforce test-driven development (TDD).

Reviews package version upgrades — diffs source between versions, traces call sites, and generates compatibility reports.

Generate a project-local verification skill that drives your app the way a user does — any language, framework, or platform.

Review payment data flows and engineering control evidence for a scoped PCI assessment, without claiming certification.

PCI DSS compliance assessment and reporting for cardholder data protection, SAQ automation, and ASV scan orchestration

Validate PCI-DSS compliance for payment card data security.

Capture performance baselines before migration for regression comparison and SLA verification

Execute load testing, stress testing, and performance benchmarking.

Use BloodHound and SharpHound (or AzureHound) to enumerate Active Directory

Investigate Active Directory compromise by analyzing authentication logs,

Conduct a focused Active Directory penetration test using BloodHound,

Detect and respond to Adversary-in-the-Middle (AiTM) phishing attacks

Use AI/LLM-based reasoning with Sherlock, theHarvester, and SpiderFoot

Simulates ARP spoofing/cache-poisoning attacks in authorized lab or

Build a multi-factor asset criticality scoring model—incorporating data

Plan and run authenticated (credentialed) vulnerability scans with scanners such as

Deploy and operate the CAPEv2 malware sandbox (a Cuckoo derivative) to run samples in a