Agent skill · Audited from source
higgsfield-websites
skill · higgsfield-ai/skillsMIT licenceAudited 27 Oct 2026 · source dd78216397f7
Is it safe? With care — CAUTION, grade B (89/100). We read this skill's source at commit dd78216397f7 and found no filesystem, network or shell access and no hard-coded secrets. The audit raised 9 findings, 0 critical or high. What it does: Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website ...`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product…
Cite
Cite this page
ModelsAtlas. “higgsfield-websites (higgsfield-ai/skills)”. Retrieved 27 Oct 2026. https://modelsatlas.com/skills/higgsfield-ai/higgsfield-websites
Trust audit
Audit 0.4.1 · source read 27 Oct 2026
CAUTION means the audit found things worth knowing before you trust this skill. Grade B is shared by 13,985 of 14,816 audited skills.
What the source does
- FilesystemNone observedNo reads or writes in the source
- NetworkNone observedNo outbound calls in the source
- ShellNone observedNo commands run in the source
- DependenciesPinnedNothing floats
- SecretsNone foundNo keys in source
Five audit layers
| Layer | What we check | Result | Findings |
|---|---|---|---|
L0 Provenance | Repo owner, licence, archive status, activity | PASS | 0 |
L1 Static source | Secrets, path traversal, supply chain, hidden code | PASS | 3 |
L2 Instructions | Prompt injection, authority framing, hidden directives | WARN | 6 |
L3 Inventory | The files and declarations match the source | PASS | 0 |
L4 Sandbox | Run in isolation and watch behaviour | SKIPPED why | 0 |
Gates applied: no behavioural pass.
Findings (9)
MEDIUMSupply chainprompt.pipe_to_shell · SKILL.md:102
curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWNetwork egressnet.metadata_ip · references/security.md:228
**Attack:** Server function accepts a URL from the client and fetches it. Attacker provides `http://169.254.169.254/latest/meta-data/` (cloud metadata), `http://localhost:8787/internal-api`, or intern
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.metadata_ip · references/security.md:774
Also check for: internal network access (`localhost`, `127.0.0.1`, `10.*`, `192.168.*`, `169.254.169.254` -- the metadata endpoint).
- Why
- cloud metadata endpoint: the classic SSRF credential grab
- Fix
- —
LOWNetwork egressnet.raw_ip · references/security.md:228
**Attack:** Server function accepts a URL from the client and fetches it. Attacker provides `http://169.254.169.254/latest/meta-data/` (cloud metadata), `http://localhost:8787/internal-api`, or intern
- Why
- No further detail recorded for this rule.
- Fix
- —
LOWPrompt injectionprompt.transfer_instruction · references/fnf-sdk.md:269
// Authenticated server function: submit the same input with its opaque token.
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · references/security.md:135
**Goals:** Access other users' data, inject content, abuse server resources, exfiltrate secrets.
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
LOWPrompt injectionprompt.transfer_instruction · references/security.md:725
- CSRF: state-changing server functions (POST/PUT/DELETE) must verify origin or use CSRF tokens. TanStack Start server functions include origin checking by default -- verify it's not disabled.
- Why
- an instruction to move sensitive data to an outside destination
- Fix
- remove; a skill never needs the user's secrets off the machine
INFOPrompt injectionprompt.credential_read · references/security.md:568
headers.set('Access-Control-Allow-Credentials', 'true'); // browser ignores * with credentials, but intent is wrong- Why
- asks the agent to read credentials
- Fix
- —
INFOPrompt injectionprompt.credential_read · references/security.md:573
headers.set('Access-Control-Allow-Credentials', 'true');- Why
- asks the agent to read credentials
- Fix
- —
Audit 0.4.1 · source sha dd78216397f7 · 27 Oct 2026Report an issue or request a re-scan
Provenance
Who published it, and what the verdict is pinned to
- Publisherhiggsfield-ai GitHub organizationOwner of the repository this skill is read from
- Source folderhiggsfield-ai/skills/higgsfield-websitesThe exact folder we audited
- LicenceMITAs the repository states it
- Commit pinned for this verdictdd78216397f7A new audit runs when the source changes
- Repository statusNot archivedPushed today
- Sandboxed runNot runSkills are read, not executed; layer L4 is skipped
What it tells the agent
Full source on GitHub ↗Its description: Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website ...`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product…
--- version: 0.13.0 name: higgsfield-websites description: | Build, edit, and deploy full-stack websites, apps and games via the Higgsfield CLI (`higgsfield website ...`). Each is a React 19 + TanStack Start SSR app in one Cloudflare Worker (D1/R2/KV/DO/Containers). THREE product types, picked via `--type` on create: `website` (standalone, no Higgsfield integration — references/website-flow.md), `app` (Sign in with Higgsfield + fnf SDK, Quanta — references/app-flow.md), `game` (realtime multiplayer rooms — references/game-flow.md). Routes to the right flow; each carries its own rules and deploy/publish gates. Use when: "build me a website", "make a landing page", "create a web app", "build a SaaS dashboard / portfolio", "make me a game", "deploy this site", "publish". Also owns GAME ART: "make a spritesheet", "tileable texture", "animate a 3D character", game music/SFX — see the game-* references. NOT for: single image/video/audio generation (higgsfield-generate), product photos (higgsfield-product-photoshoot), marketplace cards (higgsfield-marketplace-cards). argument-hint: "[what to build or edit] [--type website|app|game]" allowed-tools: Bash --- # Higgsfield website builder (CLI) — three product types, three flows You drive the whole lifecycle through the **Higgsfield CLI** (`higgsfield website ...`), then edit code on the local filesystem with `git` + `bun`. You are building ONE per-website Cloudflare Worker: a **React 19 + TanStack Start** app, **server-rendered (SSR)**, deployed as a single Worker at the product's own subdomain. The project lives in **`app/`** — run every `bun`/build command from there. ## The three types — and the REQUIRED `--type` on create `higgsfield website create` requires `--type`, and it is the **USER'S choice** — when the request doesn't make it obvious, ask the user before creating (one question, up front): - **`--type website`** — a standalone product with NO Higgsfield integration and **NO AI generation of any kind** (no image/video/audio/text generation — not via Higgsfield, and not via some other provider): no "Sign in with Higgsfield", no requests to Higgsfield, no fnf SDK. Every website gets a fully independent brand: own palette, type, and chrome from a design brief, custom Tailwind/CSS only — never import `@higgsfield/quanta/*` or use q-prefixed tokens anywhere, and no "Powered by / Built on Higgsfield" badges or mentions in page content. The user's brand is the only brand on the page. ```bash higgsfield website create --type website ``` - **`--type app`** — a product tightly integrated with Higgsfield: its users Sign in with Higgsfield and generate images/videos through the fnf SDK (the full auth + D1 contract applies). An app must look and feel like a Higgsfield product: UI built with **Quanta** (`references/quanta-design.md`) — and, for anything Quanta lacks, your own component built from Quanta primitives (never a third-party UI library) — starting from a standard app layout (`references/app-layouts.md`). Quanta and the app layouts are app-only — never applied to a `--type website` build. The independent-brand rule and the wow pipeline (`design-taste-frontend`, boards, wow catalog) are the website path; apps never get a custom brand — Quanta is the brand. ```bash higgsfield website create --type app ``` - **`--type game`** — a browser game: realtime multiplayer rooms on the game template, where the game itself is six pure functions in `app/src/logic.js` and the platform already owns sockets, rooms and persistence. Requires a **game genre** as `--category` (`arcade`, `puzzle`, `shooter`, ..., from `higgsfield website categories`) and takes **no** `--template` — a game scaffolds from the only template it can use. Single-player counts: set `minPlayers: 1`. See `references/game-flow.md`. ```bash higgsfield website create --type game --category arcade ``` **Generation is ALWAYS an app.** Any product that generates images, video, audio, or other AI media runs on Higgsfield — build it as `--type app` (Sign in with Higgsfield, generation on the user's Higgsfield credits). NEVER offer the user an option to "bring your own image/video API" or plug in their own generation key for a website — that path does not exist. `--type website` is ONLY for sites with no generation and no tie to Higgsfield or any other generation service. (A website may still use ordinary non-generation third-party APIs — payments, maps, email — with the user's own keys; that is unrelated to this rule.) Quick tells: "landing page / portfolio / marketing site / SaaS with its own users, no AI generation" → website. "generates images/video/audio, or anything with Higgsfield models, credits, or generation history" → app. "something you play — a game, multiplayer or single-player" → game. Games moved onto this pipeline from a separate engine that is being retired. The `higgsfield game ...` commands are gone: a game is created, deployed and published exactly like a website. Any doc saying otherwise is out of date. ## Always set a subdomain on create `higgsfield website create` takes an optional `--subdomain` — it becomes the site's slug, so the live URL is `<subdomain>.<host>`. **Always set it:** pick one from the product's name or purpose; only omit it (which yields a random slug) if the user explicitly wants a random one. Rules for a good subdomain: - **More than 4 characters** — short single words are reserved, so go a bit longer. - **Memorable** — derive it from the product name/purpose (e.g. `lumen-notes`, `pixelforge`), not a random string. - **Allowed characters only** — lowercase letters, digits, and single hyphens (DNS-safe). No spaces, underscores, uppercase, or leading/trailing hyphens. A few reserved labels (e.g. `api`, `www`, `app`) and already-taken subdomains are rejected — if that happens, try a close variant. ## Prerequisites 1. If `higgsfield` is not on `$PATH`, install it: ```bash
Excerpt, first 6,000 characters of SKILL.md, verbatim from the audited commit. It is text from someone else’s repository, quoted so you can judge it before your agent reads it.
Install
Pinned to the audited commit dd78216
pip install pillow npm install @material/web npm install @fluentui/react-components npm install @fluentui/web-components @fluentui/tokens npm install @carbon/react @carbon/styles npm install @radix-ui/themes
git clone https://github.com/higgsfield-ai/skills git -C skills checkout dd78216397f7
Commands as the repository documents them: shown, never run by us. Our verdict covers commit dd78216397f7 only.
Works in which agents?
What its own text says, not a test
| Agent | Status | More |
|---|---|---|
| GitHub Copilot | Mentioned in its text, not tested | Skills for GitHub Copilot · About GitHub Copilot |
| Cursor | Mentioned in its text, not tested | Skills for Cursor · About Cursor |
Audit history
Every audit, every source change
- !CAUTION B 89 / 100
first audit · source
dd78216397f7
README badge
For maintainers · shows the latest audit
[](https://modelsatlas.com/skills/higgsfield-ai/higgsfield-websites/)
The badge shows our verdict and grade for this skill, and links back to this page. It changes when the audit does.
Similar skills
obra/superpowers
Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions…
obra/superpowers
Use when you have a spec or requirements for a multi-step task, before touching code
obra/superpowers
Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions
Add this badge to your README
[](https://modelsatlas.com/skills/higgsfield-ai/higgsfield-websites/)
<a href="https://modelsatlas.com/skills/higgsfield-ai/higgsfield-websites/"><img src="https://modelsatlas.com/skills/higgsfield-ai/higgsfield-websites/badge.svg" alt="ModelsAtlas: CAUTION B"></a>
Questions about higgsfield-websites
Is higgsfield-websites safe to install?
What can higgsfield-websites access on my machine?
Which assistants does higgsfield-websites work with?
How current is this page?
Sources
- github.com/higgsfield-ai/skills/tree/main/higgsfield-websites — the audited source at commit dd78216397f7 and every finding aboveObserved · 27 Oct 2026
Spotted something wrong? Report a correction · Methodology
Keep going in your AI
Opens with this page as the source. We add nothing else to the prompt.
- Is higgsfield-websites safe to install?
- What can higgsfield-websites access on my machine?
- Which assistants does higgsfield-websites work with?