Security & Testing Agent Skills for Claude Code

Audit automatically audits AI assistant code plugins for security vulnerabilities,

Executes a comprehensive 8-phase audit pipeline to validate the structure, quality, and security of AI skills and plugins.

Find the actual cause of an admitted failure instead of a plausible one using a systematic empirical method grounded in Agans and Zeller…

Write code that resists attack — parameterizing rather than escaping, encoding for the right output context, checking authorization per…

Refute your own work before delivering it.

Pre-publish safety audit for a professional's public GitHub presence.

Secure PostHog integration: API key management, project key vs personal

Use when reviewing a pull request for security issues — automatically analyzes the diff for vulnerabilities, hardcoded secrets, injection…

Pre-commit review: security scan, quality gates, auto-fix.

Deep audit before GitHub push: removes junk files, dead code, security holes, and optimization issues.

Review prediction-market, basket, oracle, and trading-agent workflows for compliance, safety, data-quality, privacy, and execution risk.

Proactive problem identification through code analysis and pattern detection

Client-facing red-team deliverable format — codifies the Subject / Observations / Description / Impact / Recommendation / PoC structure…

Authors ModSec rules, APF/CSF/iptables/nftables firewall blocks, and LMD/ClamAV signature submissions for confirmed attack patterns.

Pressure-test a TP plan against authority, target safety, dependency integrity, validation, rollback, and release risk.

Printing Press CLI for Printing Press Golden.

Internal sub-skill: agentic review of a printed CLI's sampled command output for plausibility issues that rule-based checks can't encode…

Polish a generated CLI to pass verification and become publish-ready.

Skill for the Privacy area of Securacy. 73 symbols across 9 files.

Automatic generation of Privacy Policy based on US CCPA/CPRA + major state laws (VCDPA, CPA, CTDPA, UCPA, ICDPA, KCDPA, RIDPA). CPPA…

Probe a target for HTTP methods that should not be enabled in production — TRACE (XST attack), unrestricted PUT/DELETE, DEBUG/CONNECT…