security-passlisted
Install: claude install-skill yuri-semenenko/ai-engineering-workspace
# Security Pass
A staged security hardening workflow, distinct from a one-shot scan. The shape is: **recon → numbered checklist → approval → atomic remediation commits, typecheck-gated per task.** This matches the workflow the user validated in prior passes; follow it rather than diving straight into edits.
For a quick read-only scan of the current diff, use the built-in `/security-review` instead. This skill is for when there is real remediation work to plan and land safely.
## Phase 1 — Recon (read-only)
1. Map the attack surface relevant to the change or area: entry points (routes, handlers, server actions), trust boundaries, auth/authz checks, data flowing from untrusted input to sinks (DB, shell, HTML, file system, external calls), secret handling, and dependency surface.
2. Fan out with `Explore` subagents per subsystem when the surface is broad — keep raw findings out of the main context, per the persona's session-hygiene rule.
3. Catalog candidate issues with category + severity. Do not fix anything yet.
## Phase 2 — Numbered checklist (for approval)
Produce a single ordered checklist. Each item:
| # | Category | Severity | Location (`file:line`) | Issue | Proposed fix | Effort |
|---|---|---|---|---|---|---|
- Severity by exploitability × blast radius. Order most-critical first.
- Each item must be independently committable — that is what makes the next phase atomic.
- **Stop here and wait for approval.** The user picks which items proceed (and may defer some