More screenshots

    Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Security Review for AI-Built Apps

    1

    It skips dependencies and build caches and downgrades what it finds in tests.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Security Review for AI-Built Apps

    Security Review for AI-Built Apps

    Example session with this skill installed

    Review my repos for security problems before I promote them. Most of the code was written with AI assistants.

    • Read your context and instructions
    • Compiled the security review

    10 repositories scanned read-only in about 100 seconds. 1 repo needs action today. Real run, 2026-10-29. Project names removed.

    SeverityCountWhat
    Critical3One repo tracks its .env in git: it holds an Anthropic and an OpenAI key, and the commit is on the private GitHub remote
    High2SQL assembled with string interpolation: an offline export script (custom quoting) and an analytics script (interpolated time interval)
    Medium43 raw HTML, 6 dynamic SQL with bound values, 3 .gitignore without .env, 1 shell call in a build scriptReview list, mostly trusted static content
    Clean7 reposNothing above medium (2 with no findings at all)

    Do today (owner actions)

    1. Rotate the Anthropic key and the OpenAI key found in the tracked .env (provider dashboards). The repo is private, but a pushed key counts as exposed.
    2. git rm --cached .env, add .env to .gitignore, commit. Rewriting history is optional for a private repo once the keys are rotated.
    3. Add .env to .gitignore in the 3 repos missing it.

    Verified and kept as high: the two interpolated queries. Neither takes user input today; both should use bound parameters so a future change cannot open an injection.

    Dismissed during verification (and turned into scanner rules): keys in untracked, git-ignored local env files (fine where they are), test fixtures, Angular/Vite build caches, RLS warnings on Cloudflare D1 and on a Postgres reached only through a server API.

    Next steps offered: the manual auth review per route on the app that is live, then a SECURITY-REVIEW.md with fixes applied one per commit.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    A Claude Code skill that reviews an app built quickly with AI assistants for the mistakes that actually get such apps breached or billed: live keys in the code or in the browser bundle, committed .env files, Supabase tables without row level security, open Firebase rules, SQL built from strings, unsigned Stripe webhooks, and AI endpoints anyone can call on your budget. Read-only by default, secrets always masked, fixes only when you approve them.

    • Price: $29, one-time
    • Version: 1.0.0, updated 2026-10-29
    • Works with: Claude Code, or any agent with a shell
    • Seller: Stramanu (Emanuele Strazzullo)

    What it does

    1. Static scan with scripts/scan.py (standard library, no network, never runs your code): 17 rules for leaked keys (Stripe, AWS, Google, GitHub, Slack, OpenAI, Anthropic, private keys, Supabase service role), secrets behind public prefixes (NEXT_PUBLIC_, VITE_, EXPO_PUBLIC_...), service role in client code, committed env files, Supabase tables without RLS and using (true) policies, open Firebase rules, wildcard CORS with credentials, SQL from strings, dynamic code, shell with input, raw HTML, unverified Stripe webhooks, paid AI endpoints with no auth or rate limit. It skips dependencies and build caches and downgrades what it finds in tests.
    2. Verification: every critical and high finding is opened and confirmed or dismissed with a reason; for secrets, git history is checked to see if a key ever reached a remote.
    3. Manual review of what no scanner sees: auth and ownership checks on every route (IDOR), database rules, client bundle, payment fulfillment, AI features, uploads, admin and debug routes, headers.
    4. Report SECURITY-REVIEW.md: the 3 things to do today, findings by severity with file:line and fix, what was and was not reviewed, and the actions only you can do (key rotation, dashboard settings, history rewrite).
    5. Fixes you approve, one per commit, and a rerun of the scan with before/after counts.

    A real session

    We ran it on 10 of our own repositories (Angular, Astro, Nuxt and Workers apps, Python pipelines, D1 and Postgres databases), about 100 seconds for all of them. After verification: 3 critical findings in one repo, a tracked .env holding an Anthropic and an OpenAI key, pushed to a private remote, so both keys must be rotated and the file removed from git. 2 high: SQL assembled with string interpolation in an export script and in an analytics script. 43 medium raw-HTML renders to review, most of them of trusted static content. Seven repos had nothing above medium, two had no findings at all. Building the scanner on real code also removed the noise generic scanners produce: build caches, test fixtures, keys in untracked local env files, RLS warnings on SQLite.

    Requirements

    • Claude Code (or any agent with a shell) and Python 3
    • git for the history checks (optional)

    What you get

    The ai-app-security-review skill: workflow, scripts/scan.py with 18 tests, and references/checklist.md (what each rule means and the 10-point manual review). Single-user license.

    Limits

    Static analysis finds patterns, not every vulnerability; the manual review covers authorization, but it is not a penetration test or a certification. The skill never rotates keys, changes cloud settings, pushes or rewrites history for you: it tells you exactly what to do.

    Static analysis: it finds patterns, not every vulnerability, and it is not a penetration test. Authorization is covered by the guided manual review. Rules target JavaScript/TypeScript, Python and SQL projects. Key rotation, cloud dashboard settings and git history rewrites are done by you; the skill tells you exactly how.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed today

    Requires

    Claude Code (or any agent with a shell)
    Python 3
    git (optional, for history checks)
    Git

    Permissions

    Terminal / Shell
    Network Access
    Read Files
    Write Files

    Shell: runs scripts/scan.py (reads files, never runs project code) and read-only git commands (ls-files, log). Files: reads the repo; writes SECURITY-REVIEW.md and applies fixes only when the owner approves. Network: none for the scan; only the optional dependency audit (npm audit / pip-audit) contacts the package registry, and only with the owner's OK. The scanner contains detection patterns for secrets and dangerous code; every secret it reports is masked. It never rotates keys, pushes or changes cloud settings.

    Listedtoday

    What's inside

    Frequently Asked Questions

    This skill is specifically designed to catch security oversights common in AI-assisted development, such as 'leaked' keys in client-side bundles or missing Row Level Security (RLS) in Supabase projects. It uses a structured scanning script and checklist that goes deeper than generic LLM prompts to identify vulnerabilities that lead to data breaches or high API bills.

    It reads JavaScript/TypeScript, Python and SQL projects, whatever tool wrote them: frameworks like Next.js, Vite, Nuxt, SvelteKit, Astro and Expo, Supabase and Firebase rules, Cloudflare Workers, Stripe webhooks, and calls to OpenAI, Anthropic and Gemini. We built and tuned it on ten real repositories of our own (Angular, Astro, Nuxt, Workers, Python).

    The scanning script (scripts/scan.py, standard library, 18 tests), a reference with what each rule means and a 10-point manual review checklist, and the workflow that turns the findings into a prioritized SECURITY-REVIEW.md and, if you approve, small fixes one commit at a time.

    No, this skill performs static code scanning and logic verification to identify architectural flaws and exposed credentials. It does not conduct active network attacks, live penetration testing, or dynamic traffic analysis, so it is safe to run on your codebase without risking server stability.

    The skill is designed to be lightweight and portable, primarily requiring Python for the scanning script and standard package managers like npm or bun for dependency audits. It is intended to run in your local development environment or CI/CD pipeline rather than requiring complex cloud infrastructure.