# wendy-security-baselines

Security review rules for Wendy interop PRs: blocks bearer secrets, protects platform policy caps, and enforces proof-of-possession.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · ★ 62
- Author: wendylabsinc
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/wendylabsinc/claude-skills/tree/HEAD/wendy-security-baselines/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/wendy-security-baselines

## What it does

This skill provides a review checklist of invariants derived from the AAA contract v0.21. It inspects changes across `pki-core`, `wendy-auth`, cloud services, `wendy-proxy`, and `wendy-agent`. Under these rules, conventional bearer secrets and raw API tokens are prohibited on the wire in favor of sender-constrained tokens signed with ML-DSA-65.

SaaS-exclusive features are explicitly treated as incomplete defects. Every interop pull request must keep the self-hosted stack fully functional without relying on cloud infrastructure.

The policy ceiling lives solely inside `pki-core` config, meaning no cloud path can alter platform boundaries. In addition, SSF and CAEP streams function only as fail-safe channels: they downgrade, revoke, or terminate sessions, but never push authority increases.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add wendylabsinc/claude-skills --skill wendy-security-baselines -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/wendy-security-baselines/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/wendy-security-baselines/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add wendylabsinc/claude-skills --skill wendy-security-baselines -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/wendy-security-baselines/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add wendylabsinc/claude-skills --skill wendy-security-baselines -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/wendy-security-baselines/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install wendylabsinc/claude-skills wendy-security-baselines
```

2. **Manually: put the files in place**
- File: `.github/skills/wendy-security-baselines/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add wendylabsinc/claude-skills --skill wendy-security-baselines -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/wendylabsinc/claude-skills --path wendy-security-baselines
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/wendy-security-baselines/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add wendylabsinc/claude-skills --skill wendy-security-baselines -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/wendylabsinc/claude-skills/tree/HEAD/wendy-security-baselines/SKILL.md

## When to use it
- audit interop code against AAA contract invariants during review
- prevent unconstrained bearer tokens from reaching production
- enforce dual-path self-hosted operation on every new interop feature
- verify tamper-evident audit logging and correlation tracking across services

## Example prompts
- Review my interop pull request against wendy security baselines.
- Check our new credential issuance logic for bearer token violations.
- Audit the proxy changes to ensure platform cap boundaries remain intact.

## Similar
- [git-guardrails-claude-code](https://affpapa.org/en/nevibecode/skills/git-guardrails-claude-code.md) — skill · 499069 installs
- [ponytail-review](https://affpapa.org/en/nevibecode/skills/ponytail-review.md) — skill · 57000 installs
- [ponytail-audit](https://affpapa.org/en/nevibecode/skills/ponytail-audit.md) — skill · 45400 installs
- [security-audit](https://affpapa.org/en/nevibecode/skills/cloudflare-security-audit.md) — skill · 54800 installs
- [security-and-hardening](https://affpapa.org/en/nevibecode/skills/security-and-hardening.md) — skill · 70200 installs
- [supabase](https://affpapa.org/en/nevibecode/skills/supabase.md) — skill · 8 installs

From the same set: [wendylabsinc/claude-skills](https://affpapa.org/en/nevibecode/by/wendylabsinc/claude-skills.md) — 25 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md