Security & Testing Agent Skills for Claude Desktop

Pre-publish health check, retrofit, and audit workflow for GitHub repos.

Assess a public GitHub Skill, MCP server, agent, or small AI tool before installation by comparing its claims with static repository…

Bug bounty report writing for H1/Bugcrowd/Intigriti/Immunefi — report templates, human tone guidelines, impact-first writing, CVSS 3.1…

Use when repository access or authentication setup may affect credentials or remote state.

Performs comprehensive secret scanning and security verification across Git history and tracked files before making private repositories…

Audit a GitHub repository's security posture and hardening gaps across branch protection, CODEOWNERS, GitHub Actions, publish/release…

Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence (a screen recording by default), and…

Assess every user request before answering or acting for reasonableness, ambiguity, hidden hazards, authorization, irreversible effects…

Verify every PRD functional requirement is implemented in the branch diff — map each FR to code/spec evidence or flag it MISSING/PARTIAL

Design control traceability skill for managing user needs, design inputs, design outputs, and verification/validation linkages

Deepfake detection and media safety — detect AI-generated audio, images, video, and text, trace synthesis sources, apply watermarks…

Resolve and cross-check a machine's public IP address through bounded external services with clear disagreement and network-failure…

MUST USE for C#/.NET deterministic tests that require the smallest production seam for DateTime/Task.Delay/File/Environment/Guid/Random…

Independently and read-only review a reveal.js presentation for narrative clarity, factual support, visual hierarchy, accessibility…

Use this skill before finalizing, sharing, exporting, publishing, deploying, or reviewing any reveal.js presentation.

Audit the user's OWN project end-to-end for security vulnerabilities (known-CVE dependencies, injection, unsafe deserialization…

Reverse engineers malicious Android APK files using the JADX decompiler

Reverse engineer ransomware encryption routines to identify cryptographic

Use when BI/data access needs review for permissions, ownership and operational reliability.

Review the codebase for mission-critical files and propose cbc=mandatory .gitattributes tags for human ratification

Use to convene the adversarial-review panel before an expensive or irreversible commitment whose fate a reviewer can judge — correctness…