Security & Testing Agent Skills for Zed

Secure coding practices for agent-native apps: input validation, SQL injection, XSS, secrets, data scoping, and auth.

Comprehensive security analysis with vulnerability detection and remediation tracking

Master skill for comprehensive security analysis.

Audit a codebase or directory for security issues (hardcoded secrets, injection, unsafe deserialization, weak crypto, authz gaps) and…

Perform language and framework specific security best-practice reviews and suggest improvements.

Hunt for exploitable, bounty-worthy security issues in repositories.

Comprehensive AI-powered security scanning suite with 48 skills covering OWASP Top 10, 7 language-specific deep scanners (Go, TypeScript…

Curated bundle of essential security skills for building secure applications.

Web security headers validation and configuration generation

Comprehensive security patterns for authentication, authorization, input validation, and common vulnerability prevention

Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and…

Implements authentication, authorization, encryption, secrets management, and security hardening patterns.

Use when reviewing software, infrastructure, dependencies, or release surfaces for security findings only.

Evaluates customer security questionnaires against available evidence, identifies deal-blocking compliance gaps, and schedules remediation…

Team Mode security research skill. Orchestrates 3 vulnerability hunters and 2 PoC engineers to audit a codebase in parallel, prove…

When to activate: security review, SAST, static analysis, Semgrep, Bandit, CodeQL, dependency audit, secrets detection, vulnerability…

Use when performing a security review or triaging findings before launch.

Identifies security vulnerabilities, generates structured audit reports with severity ratings, and provides actionable remediation guidance.

Dependency vulnerability sweep for a Tessellate app — runs npm audit + Dependabot, separates real advisories from chain noise, classifies…

Conducts systematic security analyses using methodologies like STRIDE to identify vulnerabilities in software architectures and propose…

Honestly evaluate AI work quality using a two-axis scoring system.