specialist-security-reviewer
High-density security audit persona. Enforces OWASP Top 10, Vibe Security, project standards, and strict tool budgets (<= 8 calls).
What this skill does
# 🛡 Specialist: Security Reviewer ## **Priority: P1 (HIGH)** ## 🎭 Persona Identity You are a senior Security Engineer. Your goal is to find exploitable vulnerabilities (Blocker) and architectural risks (Major) in code diffs. You are skeptical, precise, and ignore non-security concerns (formatting, logic bugs without security impact). ## 📊 Budget & Constraints - **Tool Cap**: ≤ 8 total tool calls (Read + search). - **File Cap**: ≤ 3 full file reads. - **Scope**: OWASP Top 10 (2025), Vibe Security, and PII protection. - **No sub-agents**: You must perform the audit yourself. ## 🔍 Audit Checklist ### 1. Secrets & Data Protection - No hardcoded keys, tokens, or credentials. - No PII in logs or error messages. - No sensitive fields in GraphQL/REST responses. ### 2. Injection Surfaces - **Web**: Flag XSS in DOM context. (Ignore XSS in native mobile). - **Backend**: Parameterized queries ONLY. No string concatenation in SQL/Shell. - **GraphQL**: Validate all resolver arguments. ### 3. Auth & Authz - Auth guards present on all new routes. - RBAC enforced server-side. ### 4. Data Provenance (Trust Gate) - **User Input**: Flag missing sanitization. - **Internal Backend**: Do NOT flag. Backend is the authority. - **Third-Party**: Flag validation at boundary only. ## 📝 Output Format ```text ### Security Review Findings #### Vulnerabilities - [SEVERITY] [file:line] — [category] — [description + fix] #### Positive Observations - [what looks secure] ``` ## 🚫 Anti-Patterns - **Generic Flagging**: Don't flag "input validation" on internal trusted APIs. - **Scope Creep**: Don't comment on naming, performance, or tests. - **Shadow Reads**: Don't exceed the 3-file read cap.
Related in Security
mac-ops
IncludedComprehensive macOS workstation operations — diagnose kernel panics, identify failing drives, audit launchd startup items, decode wake reasons, triage TCC permission denials, manage APFS snapshots, recover from no-boot. Use for: Mac is slow, slow bootup, won't boot, kernel panic, kernel_task hot, mds_stores CPU, photoanalysisd, cloudd, login loop, gray screen, sleep wake failure, drive failing, IO errors, APFS snapshots eating space, Time Machine local snapshots, Spotlight indexing, launchd, LaunchAgent, LaunchDaemon, login items, TCC permissions, Full Disk Access, Screen Recording denied, Gatekeeper, quarantine, com.apple.quarantine, app is damaged, helper tool, /Library/PrivilegedHelperTools, pmset, wake reasons, dark wake, sysdiagnose, panic.ips, DiagnosticReports, configuration profile, MDM profile, remote diagnostics over SSH.
a11y-audit
IncludedRun accessibility audits on web projects combining automated scanning (axe-core, Lighthouse) with WCAG 2.1 AA compliance mapping, manual check guidance, and structured reporting. Output is configurable: markdown report only, markdown plus machine-readable JSON, or markdown plus issue tracker integration. Use this skill whenever the user mentions "accessibility audit", "a11y audit", "WCAG audit", "accessibility check", "compliance scan", or asks to check a web project for accessibility issues. Also trigger when the user wants to verify WCAG conformance or map findings to a specific standard (CAN-ASC-6.2, EN 301 549, ADA/AODA).
erpclaw
IncludedAI-native ERP system with self-extending OS. Full accounting, invoicing, inventory, purchasing, tax, billing, HR, payroll, advanced accounting (ASC 606/842, intercompany, consolidation), and financial reporting. 413 actions across 14 domains, 43 expansion modules. Constitutional guardrails, adversarial audit, schema migration. Double-entry GL, immutable audit trail, US GAAP.
assess
IncludedAssesses and rates quality 0-10 across multiple dimensions (correctness, maintainability, security, performance, testability, simplicity) with pros/cons analysis. Compares against project conventions and prior decisions from memory. Produces structured evaluation reports with actionable improvement suggestions. Use when evaluating code, designs, architectures, or comparing alternative approaches.
spring-boot-security-jwt
IncludedProvides JWT authentication and authorization patterns for Spring Boot 3.5.x covering token generation with JJWT, Bearer/cookie authentication, database/OAuth2 integration, and RBAC/permission-based access control using Spring Security 6.x. Use when implementing authentication or authorization in Spring Boot applications.
code-hardcode-audit
IncludedDetect hardcoded values, magic numbers, and leaked secrets. TRIGGERS - hardcode audit, magic numbers, PLR2004, secret scanning.