Security & Testing Agent Skills for Claude Desktop

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

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

Use when building apps that collect user data.

Draft a detailed privacy policy covering data types, jurisdiction, GDPR and compliance considerations, and clauses needing legal review.

Provide comprehensive techniques for escalating privileges from a low-privileged user to root/administrator access on compromised Linux…

Process Failure Mode and Effects Analysis (PFMEA) skill for manufacturing risk assessment

Processes STIX 2.1 threat intelligence bundles delivered via TAXII 2.1

Run the ProdGuard scanner on a repo to catch the security controls an AI coding agent turns off to make something work.

Autonomously deep-scan entire codebase line-by-line, understand architecture and patterns, then systematically transform it to…

End-to-end production QA, build verification, and launch-readiness checklist for fullstack Next.js apps.

Verify that browser profiles are actually isolated from one another instead of assuming it - confirm each profile's timezone agrees with…

Auditing an EXISTING software project to detect weaknesses, technical debt, and areas for improvement, evaluating it against 4 pillars…

Study, plan, harden, and verify project/workspace features with scoped files, derived knowledge, retention policies, and regression tests.

Comprehensive codebase health analysis. Use when reviewing code quality, identifying technical debt, checking dependencies, or assessing…

Run a critical, multi-dimensional quality review of the project using parallel adversarial agents.

Prompt injection detection and prevention for secure LLM applications

Write, run, and improve non-redteam Promptfoo eval suites for a configured target: test cases, assertions, rubrics, datasets, and CI gates.

QA and testing engineer — test strategy, E2E suites, API tests, flaky test triage, coverage.

Writes, reviews, and debugs property-based tests — Hypothesis, fast-check, proptest, jqwik, rapid, and Echidna or Medusa for Solidity…

Emergency defensive response when the user believes they're under active attack — hacked, compromised, credentials stolen, suspicious…

Apply after completing a task, before declaring done.