Security checklist to run before marking any task done
Scanned 9/12/2026
Install to Claude Code
Skills Directorynpx -y skills add albinotonnina/echos --skill security-checklist --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Security Checklist?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/albinotonnina-security-checklist)More formats (shields.io, HTML) on the badges page.
---
name: security-checklist
description: Security checklist to run before marking any task done
disable-model-invocation: true
---
Before reporting `status="done"`, verify each item:
**Input validation**
- [ ] All request parameters validated with Zod or a validation library
- [ ] File uploads: type, size, and filename are validated; files stored outside webroot
- [ ] Query parameters that drive DB queries use allowlists, not blocklists
**Authentication & authorisation**
- [ ] Every new endpoint has an auth middleware applied
- [ ] Authorisation checks are centralised — not ad-hoc comparisons scattered in handlers
- [ ] Password fields: never returned in API responses, never logged
**Data handling**
- [ ] No credentials, tokens, session IDs, or PII in log messages
- [ ] No sensitive values in error messages returned to clients
- [ ] All DB queries are parameterised — no string concatenation
**Transport & headers**
- [ ] New endpoints inherit the global CORS policy
- [ ] `Content-Security-Policy` header still passes for any new inline scripts/styles
**Rate limiting**
- [ ] Unauthenticated endpoints have rate limiting applied
- [ ] Auth endpoints (`/login`, `/register`, `/reset-password`) have strict rate limits (≤5 req/min)
If any item is not applicable, note why in the PR description.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...
Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.
Recovers prior coding-agent session context by running `catchup <agent> --since-compact`, which extracts a clean summary of a previous Codex, Claude Code, Antigravity, OpenCode, or Pi Agent session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", or asks to recover/summarize a previous session before continuing. Do NOT use for the current conversation, git history, or any non-agent log.
A comprehensive mathematical reasoning skill for AI assistants — handles arithmetic to research-level problems with rigorous step-by-step reasoning, systematic verification, and transparent uncertainty handling
