security-audit

security-audit is a skill for Claude Code from spawnpoint-inc/spawnpoint-plugin. It costs 101 tokens per session (2,041 once invoked), scanned A, original, MIT.

A pre-deployment security audit for an app being uploaded to Spawnpoint. It checks for exposed secrets, unsafe runtime settings, debug mode, open access controls, browser-exposed credentials, and dependency issues, and can fix some safe findings.

In plain words
What is it for?
Use it before uploading or deploying an app to check files, environment settings, CORS, admin and upload routes, credentials, and dependencies, then review the findings and verdict.
Why use it?
It catches common problems that could expose credentials or leave an app open to unwanted access before deployment. It also prevents deployment for findings that must be fixed.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the spawnpoint plugin — 3 skills, 1 MCP server shipped together

Good fit Use it before uploading or deploying an app to check files, environment settings, CORS, admin and upload routes, credentials, and dependencies, then review the findings and verdict.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/spawnpoint-inc/spawnpoint-plugin/security-audit
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.

Any agent
npx skills add spawnpoint-inc/spawnpoint-plugin --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/spawnpoint-inc/spawnpoint-plugin

Made for: Claude Code.

Or install spawnpoint, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for security-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/spawnpoint-inc/spawnpoint-plugin/security-audit/github.svg)](https://agentmods.dev/skills/spawnpoint-inc/spawnpoint-plugin/security-audit)
Your own site
<a href="https://agentmods.dev/skills/spawnpoint-inc/spawnpoint-plugin/security-audit"><img src="https://agentmods.dev/badge/skills/spawnpoint-inc/spawnpoint-plugin/security-audit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-audit

Your own site · 80×15
<a href="https://agentmods.dev/skills/spawnpoint-inc/spawnpoint-plugin/security-audit"><img src="https://agentmods.dev/badge/skills/spawnpoint-inc/spawnpoint-plugin/security-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 101 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,041 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00101 $0.02041
Opus 5.5 $0.00040 $0.00816
Sonnet 5.5 $0.00020 $0.00408
Haiku 4.5 $0.00010 $0.00204

Measured 11d ago against content hash 773b74c4a604, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 11d 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.

plugin/spawnpoint/skills/security-audit/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security audit before a spawnpoint deploy

Run it on the app directory (the argument, or the current directory) once the files are final, before create_upload or deploy_project. Install nothing. End with one table and a verdict.

The rules

  • block: no deploy_project until it is fixed or, where allowed, accepted. warn: fix it unless the user accepts. note: mention once.
  • Only two findings can never be accepted: credential content and a private-key file. The server refuses those bundles anyway.
  • Fix what is safe and say so: a port read from the environment, the bind address, a debug flag, a secret moved to env, an exclusion, and a token check on an admin, debug, or owner-only upload or presign route (generate the token, pass it as env, and give it to the owner once in your reply). Then deploy. Ask first only before changing what the app's own users get: narrowing CORS, removing a route, or making a route they use private.
  • Never print a secret you found: file, line, and kind only.
  • On a redeploy in the same session, rerun only if files changed. An acceptance holds for the session.

1. What ships

  • [block] A credential-shaped string in any text file: the seven patterns in patterns.md, with its one-line grep. Fix: move the value into env on deploy_project (or set_env), read it from the environment, and tell the user to rotate the key: it is in this transcript now. A spawnpoint bucket's key (the project's S3_* values) is rotated with rotate_storage_key.
  • [block] A credential file by name (the list in patterns.md). Fix: exclude it. .npmrc matters twice: it ships, and npm ci on the machine reads it.
  • [strip] .env, .env.*, .git/: exclude them. Name the variables .env held (never the values) and offer to pass each one as env.
  • [exclude] node_modules/, .venv/, venv/, __pycache__/, .next/, dist/ and build/ when a build script exists, .DS_Store, *.log. These become the tar --exclude flags for create_upload's command.
  • [warn] Local databases and dumps (*.sqlite, *.sqlite3, *.db, *.sql, *.dump, *.bak): ask once whether a seeded demo is intended.
  • [warn] Over about 15 MiB before compression: images first.

Read the full file on GitHub · 132 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 11d ago Changed · +9 lines · +11 tokens per session 773b74c4a604
  2. 14d ago First seen · 123 lines · 90 tokens per session scan A 50fb314ed1a0

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository spawnpoint-inc/spawnpoint-plugin (0 stars, last pushed yesterday), licensed MIT. It adds 101 tokens to every session and 2,041 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-05.

Related

Other skills, from other repositories

pinme-uniwebpay

Use when generating, modifying, or reviewing PinMe Worker (Cloudflare Worker TypeScript) code that accepts payments through UniwebPay — payment links, products/prices, checkout sessions, payment status reads, refunds, subscriptions, or handling UniwebPay webhooks with @uniwebpay/sdk in a PinMe project.

glitternetwork/pinme · 71 tokens

pinme-r2

Use when a PinMe Cloudflare Worker needs R2 object storage, including secure file or image upload, streaming download, metadata lookup, deletion, listing, Range requests, or R2+D1 coordination. Guides AI to use PinMe's automatically injected env.R2 binding without R2 credentials or manual Wrangler configuration.

glitternetwork/pinme · 68 tokens

pinme-auth

Use when a PinMe project (Worker TypeScript) needs to integrate user authentication — creating email/password users, verifying idtokens, querying user info, or listing users via Identity Platform auth proxy APIs.

glitternetwork/pinme · 44 tokens

pinme-llm

Use this skill when a PinMe project (Worker TypeScript) needs to call OpenRouter-backed LLM APIs, including models, chat/completions, streaming, or OpenRouter web search. Guides AI to generate correct Worker TS code.

glitternetwork/pinme · 54 tokens

pinme-email

Use this skill when a PinMe project (Worker TypeScript) needs to integrate email sending (sendemail). Guides AI to generate correct Worker TS code.

glitternetwork/pinme · 35 tokens

pinme-share

A tool for packaging a result as a static web page and publishing it through PinMe. A static page is a self-contained page that does not need a server to generate its content.

glitternetwork/pinme · 75 tokens