Adversarial Testing — Security skill for Claude Code
Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which phases run (PhaseAdvisor/router).
How to install Adversarial Testing
Installs to ~/.claude/skills/mickeyyaya-evolve-loop-adversarial-testing/SKILL.md
mkdir -p ~/.claude/skills/mickeyyaya-evolve-loop-adversarial-testing && curl -fsSL https://raw.githubusercontent.com/mickeyyaya/evolve-loop/HEAD/commands/adversarial-testing.md -o ~/.claude/skills/mickeyyaya-evolve-loop-adversarial-testing/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Adversarial Testing does
description: "Use when authoring evals/predicates (Scout, TDD-Engineer), framing an audit (Auditor), or justifying which phases run (PhaseAdvisor/router). Codifies Google's 4-phase adversarial-testing methodology mapped onto evolve-loop's eval, audit, routing, and red-team surfaces."
Run the **adversarial-testing** skill from
Alternatives in Security
- Yara Authoring — Trail of Bits security skill for yara authoring 3.7k ★
- /web3 Audit — Smart contract security audit using the 10-bug-class methodology 927 ★
- Senior Engineering Partner — A stack-agnostic Claude Code skill: strict code reviewer, pair programmer, debugger, and mentor (Python/Bash/A 148 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Agentguard Merchant
Policy checkpoint between AI agents and PayPal refunds: MCP security proxy, LangGraph risk pipeline with human
Gads
Google Ads playbook router. /gads [args]. Alone, shows the workspace state.
Kiro SDLC Scrum Best Practics
Ready-to-use Kiro IDE configurations for enterprise SDLC — Phase-Based (14 roles, 5 phases) and Sprint-Based D
Security TDD
SECURITY phase - Comprehensive OWASP Top 10 security audit and remediation with automatic report storage in sp
Security Audit Extended
Read-only security audit skill for coding agents. Cloudflare's audit workflow (coverage ledger, verdict contra
Sdlc Test
Phase 4 — Testing & Security. Spawns qa-manual-tester, automation-qa-engineer, appsec-engineer, penetration-te
Related Agents
Evals Engineer
Use for anything under evals/ — authoring or curating golden-set tasks, implementing the outcome/trajectory/co
Image Qc
Vision quality control of generated slideshow images. Use after every Google Flow batch, on the labelled conta
Aid Test Agent
Autonomously exercises the AID methodology end to end (Phases 0-5) and reports where it breaks. Use for /aid-t