higgsfield-game-generation

What the source does

• FilesystemDeclared3 observations
• NetworkDeclared3 observations
• ShellNone observedNo commands run in the source
• DependenciesPinnedNothing floats
• SecretsNone foundNo keys in source

Five audit layers

Gates applied: instruction override, no behavioural pass.

Do not tell the user to use `workflow get` for a job result. `workflow get` describes the workflow schema; `generate get` fetches the created job.

**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

Also check for: internal network access (`localhost`, `127.0.0.1`, `10.*`, `192.168.*`, `169.254.169.254` -- the metadata endpoint).

**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

// Authenticated server function: submit the same input with its opaque token.

**Goals:** Access other users' data, inject content, abuse server resources, exfiltrate secrets.

- 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.

headers.set('Access-Control-Allow-Credentials', 'true'); // browser ignores * with credentials, but intent is wrong

headers.set('Access-Control-Allow-Credentials', 'true');

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh -s -- --prefix=$HOME/.local

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh

Audit 0.4.1 · source sha d60a8ba7e89c · 21 Oct 2026Report an issue or request a re-scan

• Publisherhiggsfield-ai GitHub organizationOwner of the repository this skill is read from
• Source folderhiggsfield-ai/skillsThe exact folder we audited
• LicenceMITAs the repository states it
• Commit pinned for this verdictd60a8ba7e89cA new audit runs when the source changes
• Repository statusNot archivedLast push 24 days ago
• Sandboxed runNot runSkills are read, not executed; layer L4 is skipped

Its description: Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise,…

---
version: 0.13.0
name: higgsfield-brandkit
description: |
  Create and extend complete visual brand systems through the Higgsfield CLI and bundled deterministic local tooling: palettes, SVG logo marks, typography, mockups, social graphics, packaging, signage, merchandise, posters, presentation decks, and editable PPTX/PDF brandbooks. Preserves official supplied assets, persists approvals locally, and regenerates only dependent outputs. Use when: "create a brand kit", "make a visual identity", "design a logo and brandbook", "apply this logo to branded assets", "make packaging or signage", or "extend our existing branding". Chain with higgsfield-generate for general image production and Marketing Studio brand-kits when importing website metadata for ads. NOT for unbranded image generation (use higgsfield-generate), product catalog photography (use higgsfield-product-photoshoot), website implementation (use higgsfield-websites), or native Figma/Canva/PSD/AI delivery.
argument-hint: "[brand brief or existing assets] [requested deliverables]"
allowed-tools: Bash
---

# Higgsfield Brandkit

Build a coherent identity and its requested applications. Treat supplied brand facts and official assets as fixed constraints.

## Bootstrap

1. Resolve `SKILL_ROOT` to this skill's installed directory and create a durable project directory:

   ```bash
   BRANDKIT_WORKDIR="${PWD}/brandkit"
   BRANDKIT_STATE="${BRANDKIT_WORKDIR}/state.json"
   mkdir -p "${BRANDKIT_WORKDIR}"
   ```

2. Read [prerequisites](references/prerequisites.md). Check tools before the stage that needs them. Never install system packages without the user's permission.
3. If `higgsfield` is missing, install it only after permission:

   ```bash
   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
   ```

4. If `higgsfield account status` fails with an authentication or workspace error, ask the user to run `higgsfield auth login` or select a workspace, then wait.
5. Inspect live model contracts before paid generation:

   ```bash
   higgsfield model get recraft_v4_1 --json
   higgsfield model get seedream_v5_pro --json
   higgsfield model get gpt_image_2 --json
   ```

## CLI mapping

| Operation | Command |
|---|---|
| Discover a model | `higgsfield model get <model> --json` |
| Generate and poll | `higgsfield generate create <model> ... --wait --json` |
| Resume a job | `higgsfield generate wait <job_id> --json` |
| Upload a local asset | `higgsfield upload create <path> --json` |
| Import website metadata | `higgsfield marketing-studio brand-kits fetch --url <url> --wait --json` |
| Read/write approval state | `python3 "$SKILL_ROOT/scripts/brandkit.py" state ...` |
| Render review boards | `python3 "$SKILL_ROOT/scripts/brandkit.py" preview ...` |
| Inspect selected logo | `python3 "$SKILL_ROOT/scripts/brandkit.py" logo-inspect ...` |
| Export logo files | `python3 "$SKILL_ROOT/scripts/brandkit.py" logo-export ...` |
| Build a Brandbook | `python3 "$SKILL_ROOT/scripts/brandkit.py" brandbook-build ...` |

Local image paths passed with `--image` are auto-uploaded. Keep HTML, SVG, PPTX, and PDF deliverables as local project files unless the user explicitly needs a hosted copy.

## User-facing behavior

- Match the user's language. Keep Design Brain reasoning, prompts, state mechanics, scripts, model lookup, and QA internals private.
- Send at most one short status sentence per visible generation batch, then stay quiet until the result is ready.
- Ask one compact set of only unresolved blocking questions. Never repeat facts or force a complete identity questionnaire for a partial task.
- After each palette, logo, typography, or downstream review, stop and wait for ordinary user feedback.
- Never infer approval from silence, successful generation, or your own preference.
- Preserve exact user copy. Never invent positioning, values, claims, ingredients, prices, certifications, statistics, or regulatory content.

## Core workflow

1. **Classify the request.**
   - `apply-existing`: use supplied official assets without redesigning them.
   - `extend-partial`: create only missing slots required by the requested output.
   - `create-identity`: create a new logo or identity only when explicitly requested.
2. **Read state.** Run:

   ```bash
   python3 "$SKILL_ROOT/scripts/brandkit.py" state \
     --state-file "$BRANDKIT_STATE" --action get_status
   ```

   Local state is durable. Never paste, hand-edit, or recreate approvals when the state file exists.
3. **Run intake and asset analysis.** Read [intake](references/intake.md), [asset analysis](references/asset-analysis.md), [state routing](references/handoff.md), and [exact state payloads](references/state-payloads.md). Lock every user-declared official logo, palette, and typography slot immediately.
4. **Create the Brand Lock.** Read [Brand Lock](references/brand-lock.md). Record exact spelling, official assets, colors, fonts, layout/shape rules, requested outputs, and forbidden treatments.
5. **Require only the slots the output uses.**
   - logo-only → palette + logo for a new mark; official logo alone for an existing mark
   - palette-only → palette
   - typography-only → typography
   - copy-free mockup/merch → logo; add palette only when color/application requires it
   - text-bearing social/packaging/poster/signage → logo + palette + typography
   - Brandbook/deck → logo + palette + typography
6. **Build missing foundation slots.** Read [Design Brain](references/brandkit-design-brain.md), [concept boards](references/concept-boards.md), [inline reviews](references/inline-widgets.md), and only the needed [palette](references/palette.md), [logo](references/logo.md), or [typography](references/typography.md) module.
7. **Continue the original request** as soon as its required slots are approved. Never ask the user to choose scope again.
8. **Load only the requested production module:**
   - [mockups](references/mockups.md)
   - [social graphics](references/

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.

1. 2026-10-21
   !CAUTION C 79 / 100

   first audit · source d60a8ba7e89c

Questions about higgsfield-game-generation

• github.com/higgsfield-ai/skills — the audited source at commit d60a8ba7e89c and every finding aboveObserved · 21 Oct 2026

Spotted something wrong? Report a correction · Methodology