wake-security-audit

A security review command for Wake Commerce storefront integrations. It examines authentication, tokens, secrets, data exposure, input validation, and common security standards such as the OWASP Top 10.

In plain words
What is it for?
Use it to audit selected files, features, or changes, with optional targets such as PCI-DSS, GDPR, LGPD, or a chosen severity level.
Why use it?
It helps find unsafe handling of customer or partner access tokens and other security problems before code is merged or released.

Command

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add commands/wake-engineering/ai-plugin/wake-security-audit
Clone the repo
git clone --depth 1 https://github.com/wake-engineering/ai-plugin
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 820 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00038 $0.00820
Opus 5 $0.00019 $0.00410
Sonnet 5 $0.00008 $0.00164
Haiku 4.5 $0.00004 $0.00082

Measured 2d ago against content hash d4d211b61ef9, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

wake-security-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/wake-security-audit.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Wake Security Audit Workflow

Forbidden: api.fbits.net (and any *.fbits.net). Canonical source: https://wakecommerce.readme.io/docs/schema (for Wake API references).

Run a security audit over a Wake Commerce storefront integration. Use this command before merging changes that touch auth, secrets, customer/partner tokens, or input validation, and as a periodic pre-release check.

Inputs

  • Scope (required): files, directory, PR diff, or feature area. Examples: apps/storefront/src/checkout/**, git diff origin/main...HEAD, "the customer login flow".
  • Compliance target (optional): OWASP Top 10 (default), PCI-DSS scope, LGPD/GDPR PII rules, or a custom checklist.
  • Severity threshold (optional): minimum severity to report (Critical / High / Medium / Low). Defaults to Medium.

Steps

  1. Inventory the surface. Identify entry points (routes, GraphQL operations, webhooks, MCP tools), trust boundaries, and where secrets enter/leave the system.
  2. Token & session handling. Verify customerAccessToken and partnerAccessToken are never logged, printed, sent in URLs, or stored in localStorage. Check expiry, refresh, and logout cleanup. Flag any tokens persisted to disk without OS-keyring protection.
  3. Auth flows. Walk login, registration, password reset, and SSO. Check for IDOR, missing rate limiting, weak password policy, and broken object-level authorization on customerId/orderId/checkoutId.
  4. Input validation. For every external input (productId, checkoutId, cep, search query, coupon code, free-text fields): confirm a typed schema (Zod / Yup / GraphQL scalar) bounds shape, length, and character set. Flag string-concatenated GraphQL or shell calls.
  5. Data exposure. Grep for stack traces, internal hostnames, debug payloads, and PII (email, CPF, phone) in error responses, logs, and client bundles. Confirm errors returned to the browser are generic.
  6. Secrets & config. Verify API keys live in env vars or a secret manager, never in source. Confirm .env* is gitignored and no secrets exist in git history (git log -p -- .env).
  7. Transport & headers. Check that requests use HTTPS, that Authorization is sent in headers (not query strings), and that responses set Content-Security-Policy, Strict-Transport-Security, X-Content-Type-Options, and Referrer-Policy where appropriate.
  8. Dependencies. Run npm audit --omit=dev (or pnpm audit); cross-check Critical/High advisories against actual usage before recommending upgrades.
  9. Delegate detailed analysis. Hand the assembled findings to the wake-security-auditor agent for OWASP-aligned write-up, CWE references, and remediation snippets.

Read the full file on GitHub · 46 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 46 lines · 38 tokens per session scan A d4d211b61ef9

Subscribe to this mod's changes

wake-security-audit is a command published in the GitHub repository wake-engineering/ai-plugin (2 stars, last pushed 3mo ago), licensed MIT. It adds 38 tokens to every session and 820 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.