From security
Review identity and access management — auth flows, RBAC, session management, and permission boundaries
npx claudepluginhub silviaare95/xari-plugins --plugin securityThis skill uses the workspace's default tool permissions.
Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Review scope: $ARGUMENTS
httpOnly: true (prevents XSS token theft)secure: true (HTTPS only)sameSite: 'lax' or 'strict' (CSRF protection)alg: none)?## IAM Review: <scope>
### Risk Summary
| Area | Risk Level | Key Issue |
|------|-----------|-----------|
| Auth flow | low/medium/high | <summary> |
| Sessions | low/medium/high | <summary> |
| RBAC | low/medium/high | <summary> |
### Critical Findings
1. **<finding>**: <risk + fix>
### Recommendations
1. **<recommendation>**: <rationale>
### Auth Flow Diagram
[Client] → POST /auth/login (email, password) ← Set-Cookie: session=<token> (httpOnly, secure, sameSite) → GET /api/resource (Cookie: session=<token>) ← 200 OK (authorized) | 403 Forbidden (wrong role)