Skip to content
skillsafebeta
← Report library
Purpose / Other

Higgsfield Generate Skill Security Audit

What the author says it does (original text)

|

Independent security check

Do not install or run it yet

Files checked
13
Risks found
7
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.Risks found: 2
High risk

Runs a downloaded program right away

Source references: 2
What we found

This line runs the downloaded content without giving you a chance to read it first.

Why this matters

Once run, the downloaded program could read or change your files. The owner of the website can also replace the program without changing its URL.

This is an active installation instruction used when `higgsfield` is absent: it pipes GitHub's current response directly into a shell. No commit or checksum is pinned. If the remote content or delivery chain is compromised, code runs with the current user's permissions and could access or alter reachable data. A user can require a pinned release, checksum, and a download-then-review installation method.

SKILL.md:37In the instructionsOpen original file
   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh   ```
Show 1 other places
SKILL.md:35In the instructionsOpen original file
1. If `higgsfield` is not on `$PATH`, install it:   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh   ```2. If `higgsfield account status` fails with `Session expired` / `Not authenticated`, ask the user to run `higgsfield auth login` (interactive) and wait for confirmation.
High risk

Executes a network-downloaded installer directly in a shell

Source references: 2
What we found

If the CLI is missing, the Skill pipes whatever GitHub currently returns directly into a shell, without a pinned release, commit hash, checksum, or review step.

Why this matters

If the URL, publishing account, network path, or script is compromised, the installer can execute arbitrary commands with the agent's permissions and access or alter user files and credentials.

The candidate matches the live bootstrap flow: when the CLI is missing, the Skill executes a network-fetched script from the `main` branch, with no visible version pin, hash verification, or review step. This is not merely an example or warning; it is required before other commands. A user can ask for a verifiable pinned release and restrict installation filesystem and network permissions.

SKILL.md:33In the instructionsOpen original file
Before any other command:1. If `higgsfield` is not on `$PATH`, install it:   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh   ```2. If `higgsfield account status` fails with `Session expired` / `Not authenticated`, ask the user to run `higgsfield auth login` (interactive) and wait for confirmation.
Show 1 other places
SKILL.md:31In the instructionsOpen original file
## Step 0 — BootstrapBefore any other command:1. If `higgsfield` is not on `$PATH`, install it:   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh   ```2. If `higgsfield account status` fails with `Session expired` / `Not authenticated`, ask the user to run `higgsfield auth login` (interactive) and wait for confirmation.
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.Risks found: 2
High risk

Local photos, videos, and voice samples are automatically uploaded to a third party

Source references: 5
What we found

The Skill explicitly auto-uploads media paths and includes flows for founder photos, voice references, and advertising videos. It does not require disclosure of the recipient or retention period, or confirmation that depicted people consented.

Why this matters

Faces, voices, unreleased advertisements, client assets, or embedded metadata can leave the device and become subject to third-party processing, storage, and account-retention rules.

Local paths are automatically uploaded, including photos, videos, and audio; examples cover a founder avatar and an ad sent for analysis. Uploading is part of the requested generation service, not evidence of covert theft, but it transfers potentially sensitive faces, voices, or business media to Higgsfield. The visible instructions do not require a pre-upload confirmation covering recipient, retention, or subject consent. Users can require confirmation for every upload and provide only authorized, minimized media.

references/media-inputs.md:5In the instructionsOpen original file
## Path or UUID — both workEach media flag accepts either a local file path or a UUID. The CLI auto-uploads paths before submission and auto-detects whether a UUID is an upload id (from `higgsfield upload create`) or a previous job id.
Show 4 other places
references/marketing-avatars.md:23In the instructionsOpen original file
```bashID=$(higgsfield upload create founder.png)URL=$(higgsfield upload create founder.png --json | jq -r .url)   # if you need cloudfront URLhiggsfield marketing-studio avatars create --name "Founder" --image $ID --image-url $URL```
references/media-inputs.md:19In the instructionsOpen original file
# Video analysis — CLI uploads the file, Virality Predictor returns a text score/report plus an Open report link.# The output is text, but the task is still video analysis.higgsfield generate create brain_activity --video ./ad.mp4 --wait```
references/media-inputs.md:103In the instructionsOpen original file
higgsfield generate create seed_audio \  --prompt "same voice, calmer delivery" \  --audio-references ./voice.wav \  --wait```
references/marketing-avatars.md:21In the instructionsOpen original file
## Creating a custom avatar```bashID=$(higgsfield upload create founder.png)URL=$(higgsfield upload create founder.png --json | jq -r .url)   # if you need cloudfront URLhiggsfield marketing-studio avatars create --name "Founder" --image $ID --image-url $URL````--image-url` is the cloudfront URL from the upload. Required by the API.
Medium risk

Uploaded assets become reusable account objects without a documented cleanup path

Source references: 6
What we found

Ad references are processed and stored by the backend, while avatars, products, and brand metadata are created as reusable entities. The supplied instructions show create, list, and inspect operations but no visible deletion or retention control.

Why this matters

Face photos, product assets, reference videos, and imported brand metadata may remain in the account after a one-off job, increasing exposure to later misuse or account compromise.

Ad references are explicitly processed, stored, and reusable later; avatars and products are also created as account entities. The visible documentation supplies create, list, and get flows but no deletion command or retention period, so personal or commercial media may remain as reusable objects. This does not prove the service has no deletion capability. Before uploading, users can ask the author to document retention, access scope, and deletion, and avoid unnecessary persistent objects.

references/marketing-ad-references.md:3In the instructionsOpen original file
Ad references are reusable inspiration videos a user wants to model new ads after — typically tied to a specific avatar and/or product. The backend processes the input video and stores a reusable reference the user can recall later.
Show 5 other places
references/marketing-ad-references.md:52In the instructionsOpen original file
The backend kicks off processing asynchronously. Newly created references start in `status: queued` then move to `in_progress` and finally `completed` (or `failed`).
references/marketing-brand-kits.md:3In the instructionsOpen original file
A brand kit captures a brand's identity (name, logo, hero images, colours, fonts, tone, products) and is reused across image generations to keep visuals on-brand.This is a Marketing Studio metadata import for ad generation, not a visual-identity design workflow. For a new or extended logo, palette, typography system, applications, or editable Brandbook, route to `higgsfield-brandkit` instead. Use this page only to fetch website metadata into a Marketing Studio brand-kit ID.A kit is created by handing in a website URL — it is being fetched and fields are being filled.
references/marketing-products.md:3In the instructionsOpen original file
Two ways to register a product: URL fetch (auto-imports title, description, images) or manual (provide your own).
references/marketing-ad-references.md:54In the instructionsOpen original file
## Discover```bashhiggsfield marketing-studio ad-references listhiggsfield marketing-studio ad-references list --jsonhiggsfield marketing-studio ad-references list --size 50 --cursor <cursor>```
references/marketing-ad-references.md:70In the instructionsOpen original file
## Inspect```bashhiggsfield marketing-studio ad-references get <id>higgsfield marketing-studio ad-references get <id> --json```
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.No risks found
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.No risks found
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 3
Medium risk

Defaults can submit credit-consuming high-quality jobs without showing the cost

Source references: 4
What we found

The Skill says not to estimate cost unless asked and to prefer the quality default, after which the generic flow directly creates and waits for a job.

Why this matters

A user can incur charges without seeing expected credits, model price, or batch cost, particularly for 4K output, longer video, or multiple advertisement images.

The Skill explicitly says not to estimate cost by default, prefers quality-first models, and then creates and waits for jobs in the generic flow. A cost command exists, showing that preflight estimation is possible but reserved for when the user asks. A request without an explicit budget may therefore consume credits, potentially at a costlier quality tier. Users can require a credit quote and confirmation before every submission and cap batch size, resolution, and retries.

SKILL.md:48In the instructionsOpen original file
4. Don't batch-ask. Pick a sane default model and ask one thing at a time only if genuinely missing.5. Don't pre-estimate cost or optimize for cheaper models unless the user asks. Prefer the quality default first.6. Pass `--wait` to `generate create` so the command blocks until done and prints the result URL itself. Avoid the two-step `create` → `wait` pattern.
Show 3 other places
SKILL.md:124In the instructionsOpen original file
3. **Validate quickly.** If unsure of params, run `higgsfield model get <jst> --json` once and pass only what's needed. Validate the preferred model before falling back to an older one. Use schema defaults otherwise. The server returns `adjustments` for non-fatal coercions (e.g. `aspect_ratio=99:99` → closest match) and a structured error for invalid declared-param values.4. **Submit and wait in one shot.** `higgsfield generate create <jst> [--prompt "..."] [media flags] [param flags] --wait`. Blocks until terminal status and prints the result on stdout. Tunables: `--wait-timeout 20m` (default 10m), `--wait-interval 5s` (default 3s). Virality Predictor does not need a prompt; pass `--video`.5. **Deliver.** For generated media and 3D assets, send the primary result URL plus a one-line summary (model, duration if video; GLB/asset URL for 3D). For Virality Predictor, deliver the scores, business interpretation, and the Open report link. Do not surface Virality Predictor `.glb`, `.bin`, or region-table internals in normal chat output.
references/marketing-dtc-ads.md:67In the instructionsOpen original file
| `--quality` | no | `low` | `low, medium, high` || `--batch-size` | no | `1` | 1..20 || `--media` | no | — | Repeatable, ≤14. Format: `<media_input_id>[:role]` (default role `image`). || `--avatar` | no | — | Max 1. Format: `<avatar_id>[:type]` (default type `preset`; use `custom` for user-uploaded avatars). || `--product` | no | — | Max 1. Product UUID from `marketing-studio products list`. || `--folder-id` | no | — | Folder placement. || `--from-file` | no | — | JSON file with the params shape. Flags merge over file values (flags win). || `--cost-only` | no | `false` | Print credit cost; do not create a job. || `--wait` | no | `false` | Poll until terminal status, then print the result URL. || `--timeout` | no | `5m` | Wait timeout. |
references/troubleshooting.md:30In the instructionsOpen original file
## Cost`higgsfield generate cost <jst> ...` returns credit estimate without submitting. Useful when the user asks "how much will this cost?".
Medium risk

Invalid parameters may be changed to approximate values and generation can continue

Source references: 4
What we found

The documentation says unsupported closed-enum values are clamped to the closest allowed value and processing continues. The generic flow notes returned `adjustments` but does not require user approval before a paid submission.

Why this matters

Aspect ratio, duration, or other output properties may differ from the request while still consuming credits, which is significant for advertisements or client deliverables with fixed specifications.

The documentation says an unsupported closed-enum value may be changed to the nearest allowed value and generation continues, while the generic flow then submits immediately. This can produce and charge for an output whose aspect ratio or other setting differs from the request; the visible flow reports `adjustments` but does not require approval before submission. Not every error is coerced—unknown parameters remain fatal. Users can require the process to stop on any adjustment and show final parameters before resubmission.

SKILL.md:123In the instructionsOpen original file
2. **Pass media inputs straight to flags.** Media flags accept a local file path **or** a UUID. CLI auto-uploads paths and auto-detects job vs upload for UUIDs. No need to pre-upload. Each model declares accepted media roles or `*_references` params — see `references/media-inputs.md`.3. **Validate quickly.** If unsure of params, run `higgsfield model get <jst> --json` once and pass only what's needed. Validate the preferred model before falling back to an older one. Use schema defaults otherwise. The server returns `adjustments` for non-fatal coercions (e.g. `aspect_ratio=99:99` → closest match) and a structured error for invalid declared-param values.4. **Submit and wait in one shot.** `higgsfield generate create <jst> [--prompt "..."] [media flags] [param flags] --wait`. Blocks until terminal status and prints the result on stdout. Tunables: `--wait-timeout 20m` (default 10m), `--wait-interval 5s` (default 3s). Virality Predictor does not need a prompt; pass `--video`.5. **Deliver.** For generated media and 3D assets, send the primary result URL plus a one-line summary (model, duration if video; GLB/asset URL for 3D). For Virality Predictor, deliver the scores, business interpretation, and the Open report link. Do not surface Virality Predictor `.glb`, `.bin`, or region-table internals in normal chat output.
Show 3 other places
references/model-catalog.md:196In the instructionsOpen original file
These are model-specific. The CLI clamps unsupported values to the nearest allowed one (with a `Note: adjustments applied` warning) when the model declares a closed set. When in doubt:
references/model-catalog.md:217In the instructionsOpen original file
- **Adjustments** — a non-fatal coercion. E.g. you passed `aspect_ratio=99:99` and the model accepts a closed set; the CLI picks the closest match and continues. The adjustments map is included in the response.- **Validation error** — a fatal mismatch. E.g. an unknown declared parameter, or a media role the model doesn't accept. The CLI returns an error and does not submit.
references/model-catalog.md:215In the instructionsOpen original file
The CLI reports two kinds of feedback:- **Adjustments** — a non-fatal coercion. E.g. you passed `aspect_ratio=99:99` and the model accepts a closed set; the CLI picks the closest match and continues. The adjustments map is included in the response.- **Validation error** — a fatal mismatch. E.g. an unknown declared parameter, or a media role the model doesn't accept. The CLI returns an error and does not submit.
Medium risk

Model-generated virality scores are framed as an objective basis for business decisions

Source references: 3
What we found

The Skill instructs the agent to describe Virality Predictor as an “objective attention proxy” and infer stimulation, focus, and mind-wandering from regional scores, without visible validation scope, error bounds, or target-population limits.

Why this matters

Users may reject creative work, shift advertising budgets, or evaluate staff based on an opaque model inference presented as objective measurement, leading to poor commercial decisions.

The live instructions call the score an “objective attention proxy” and connect higher region scores and lower Default Mode with focus and less mind-wandering. The visible material supplies no validation study, error range, or applicable population, so users could treat it with undue certainty in advertising or content decisions. This supports a decision-risk concern, not a claim that the score is wrong. Users can request methodology and validation limits and restrict it to a secondary signal rather than a sole decision basis.

SKILL.md:278In the instructionsOpen original file
Use Virality Predictor (`brain_activity`) when the user wants to evaluate a finished video as a business creative: hook strength, virality potential, attention, retention, or how well the content/product holds focus and minimizes distraction. Treat "Virality Predictor" as the customer-facing feature name; `brain_activity` is only the CLI/job_set_type.
Show 2 other places
SKILL.md:284In the instructionsOpen original file
The result is text, not a generated image/video. Report the overall score, peak hook second, sustain score, strongest/weakest regions, and report URL if present. Interpret it as an objective attention proxy for creative testing: higher Visual/Auditory/Language/Attention scores suggest stronger stimulus and focus; lower Default Mode is better because it suggests less mind-wandering.
references/model-catalog.md:89In the instructionsOpen original file
|---|---|---|| Virality Predictor (`brain_activity`) | Higgsfield | **Objective attention proxy for video creative testing.** Scores how effectively a clip captures and sustains attention, useful for hook validation, virality potential, ad review, and product/content focus. Takes a video input and returns a text report with overall score, peak second, sustain, and an Open report link. Raw `.glb` / `.bin` render artifacts stay in JSON/debug output. |

Inside this skill

8 instruction sections

The Skill uses a third-party `higgsfield` CLI with Bash access to submit image, video, 3D, and audio jobs, normally waiting for the remote job to finish.

View source
SKILL.md:24In the instructionsOpen original file
argument-hint: "[prompt-or-analysis-request] [--model <name>] [--image|--video <path-or-id>]"allowed-tools: Bash---
SKILL.md:29In the instructionsOpen original file
Submit jobs to any Higgsfield model. Wraps the `higgsfield` CLI. Covers generic image/video/3D/audio generation, Marketing Studio (branded ads, avatars, products, hooks, settings), and, secondarily, Virality Predictor video scoring.
SKILL.md:124In the instructionsOpen original file
3. **Validate quickly.** If unsure of params, run `higgsfield model get <jst> --json` once and pass only what's needed. Validate the preferred model before falling back to an older one. Use schema defaults otherwise. The server returns `adjustments` for non-fatal coercions (e.g. `aspect_ratio=99:99` → closest match) and a structured error for invalid declared-param values.4. **Submit and wait in one shot.** `higgsfield generate create <jst> [--prompt "..."] [media flags] [param flags] --wait`. Blocks until terminal status and prints the result on stdout. Tunables: `--wait-timeout 20m` (default 10m), `--wait-interval 5s` (default 3s). Virality Predictor does not need a prompt; pass `--video`.5. **Deliver.** For generated media and 3D assets, send the primary result URL plus a one-line summary (model, duration if video; GLB/asset URL for 3D). For Virality Predictor, deliver the scores, business interpretation, and the Open report link. Do not surface Virality Predictor `.glb`, `.bin`, or region-table internals in normal chat output.

Local media paths are automatically uploaded by the CLI. Inputs can include photos, videos, audio, face avatars, voice references, and advertising videos submitted for analysis.

View source
references/media-inputs.md:7In the instructionsOpen original file
Each media flag accepts either a local file path or a UUID. The CLI auto-uploads paths before submission and auto-detects whether a UUID is an upload id (from `higgsfield upload create`) or a previous job id.
references/marketing-avatars.md:21In the instructionsOpen original file
## Creating a custom avatar```bashID=$(higgsfield upload create founder.png)URL=$(higgsfield upload create founder.png --json | jq -r .url)   # if you need cloudfront URLhiggsfield marketing-studio avatars create --name "Founder" --image $ID --image-url $URL```
references/media-inputs.md:103In the instructionsOpen original file
higgsfield generate create seed_audio \  --prompt "same voice, calmer delivery" \  --audio-references ./voice.wav \  --wait```

Marketing Studio can create reusable products, avatars, ad references, and brand metadata in the user's account; some objects are processed and stored asynchronously by the backend.

View source
SKILL.md:174In the instructionsOpen original file
- **Avatar** — presenter face. Curated `preset` (browse `higgsfield marketing-studio avatars list`) or `custom` (uploaded photos via `higgsfield marketing-studio avatars create`). For UGC modes, an avatar is optional if the brief clearly mentions a person; the backend can create a Soul Character automatically. Pass an avatar when the user wants a specific presenter.- **Product** — brand item with title + reference images. Imported from URL (`higgsfield marketing-studio products fetch --url ...`) or created from uploaded images (`higgsfield marketing-studio products create`).- **Webproduct** — App Store / web page version. Auto-routes when fetching App Store URLs.- **Hook** — reusable opening angle / ad hook. Browse with `higgsfield marketing-studio hooks list`. Hook text is prepended to the user's prompt; it does not replace `--prompt`.- **Setting** — reusable environment / scene context. Browse with `higgsfield marketing-studio settings list`.- **Ad reference** — reusable inspiration video that can be bound to an avatar and/or product. Created from an uploaded video (`--video-input <upload_id>`) or a previous generation job (`--job <job_id>`). Browse with `higgsfield marketing-studio ad-references list`. See `references/marketing-ad-references.md`.- **Brand kit** — captures a brand's identity (name, logo, hero images, colours, fonts, tone) for reuse across image generations. Created by handing in a website URL (`higgsfield marketing-studio brand-kits fetch --url https://… --wait`). See `references/marketing-brand-kits.md`.- **Ad format** — presets that drives the visual structure of a generated image (`headline`, `bullet-points`, etc.). Read-only, browse with `higgsfield marketing-studio ad-formats list`. Required input for `dtc-ads generate`.
references/marketing-ad-references.md:52In the instructionsOpen original file
The backend kicks off processing asynchronously. Newly created references start in `status: queued` then move to `in_progress` and finally `completed` (or `failed`).

Virality Predictor sends a finished video to a remote model and returns attention, retention, and virality scores plus a report link for creative testing.

View source
SKILL.md:278In the instructionsOpen original file
Use Virality Predictor (`brain_activity`) when the user wants to evaluate a finished video as a business creative: hook strength, virality potential, attention, retention, or how well the content/product holds focus and minimizes distraction. Treat "Virality Predictor" as the customer-facing feature name; `brain_activity` is only the CLI/job_set_type.
SKILL.md:284In the instructionsOpen original file
The result is text, not a generated image/video. Report the overall score, peak hook second, sustain score, strongest/weakest regions, and report URL if present. Interpret it as an objective attention proxy for creative testing: higher Visual/Auditory/Language/Attention scores suggest stronger stimulus and focus; lower Default Mode is better because it suggests less mind-wandering.The CLI prints an Open report URL like `https://<app-domain>/apps/virality-predictor?resultJobId=<job_id>`. Send that URL for the visual report. Raw artifact URLs such as `brain_example_url`, `vertexMapBinaryUrl`, and `vertexMapUrl` are implementation details; mention them only when the user asks for raw data or implementation details.
Start here · InstructionsSKILL.md
higgsfield-generate
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 2 more sections are available in the original file.

File reference map

References: 12
Files making referencesReferenced content
Lines show actual file references, not execution order. Select a node to highlight its connections and inspect the files and source locations. Dashed lines include files that still need locating.
Files and check records13 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included
  • references/marketing-ad-references.mdFull text included
  • references/marketing-avatars.mdFull text included
  • references/marketing-brand-kits.mdFull text included
  • references/marketing-dtc-ads.mdFull text included
  • references/marketing-modes.mdFull text included
  • references/marketing-products.mdFull text included
  • references/marketing-setup-items.mdFull text included
  • references/media-inputs.mdFull text included
  • references/model-catalog.mdFull text included
  • references/prompt-engineering.mdFull text included
  • references/troubleshooting.mdFull text included
  • references/workflows.mdFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions
  • references/marketing-ad-references.mdSupporting file
  • references/marketing-avatars.mdSupporting file
  • references/marketing-brand-kits.mdSupporting file
  • references/marketing-dtc-ads.mdSupporting file
  • references/marketing-modes.mdSupporting file
  • references/marketing-products.mdSupporting file
  • references/marketing-setup-items.mdSupporting file
  • references/media-inputs.mdSupporting file
  • references/model-catalog.mdSupporting file
  • references/prompt-engineering.mdSupporting file
  • references/troubleshooting.mdSupporting file
  • references/workflows.mdSupporting file

Operations mentioned in code and instructions

Run commands
SKILL.md:24In the instructionsOpen original file
argument-hint: "[prompt-or-analysis-request] [--model <name>] [--image|--video <path-or-id>]"allowed-tools: Bash---
SKILL.md:36In the instructionsOpen original file
1. If `higgsfield` is not on `$PATH`, install it:   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh
SKILL.md:149In the instructionsOpen original file
```bashhiggsfield generate create gpt_image_2 --prompt "neon city at dusk" --aspect_ratio 16:9 --resolution 2k --wait
Connect to websites
SKILL.md:37In the instructionsOpen original file
   ```bash   curl -fsSL https://raw.githubusercontent.com/higgsfield-ai/cli/main/install.sh | sh   ```
SKILL.md:180In the instructionsOpen original file
- **Ad reference** — reusable inspiration video that can be bound to an avatar and/or product. Created from an uploaded video (`--video-input <upload_id>`) or a previous generation job (`--job <job_id>`). Browse with `higgsfield marketing-s …- **Brand kit** — captures a brand's identity (name, logo, hero images, colours, fonts, tone) for reuse across image generations. Created by handing in a website URL (`higgsfield marketing-studio brand-kits fetch --url https://… --wait`). See `references/marketing-brand-kits.md`.- **Ad format** — presets that drives the visual structure of a generated image (`headline`, `bullet-points`, etc.). Read-only, browse with `higgsfield marketing-studio ad-formats list`. Required input for `dtc-ads generate`.
SKILL.md:251In the instructionsOpen original file
# 1. Trigger fetch (returns the product id, import runs in the background)higgsfield marketing-studio products fetch --url https://shop.example.com/sneakers --wait
Read keys or account settings
references/troubleshooting.md:6In the instructionsOpen original file
- `Session expired.` → `higgsfield auth login`- `Stored credentials are for ... but current environment ...` → `higgsfield auth login` for the current API URL.- `Not authenticated.` → first `higgsfield auth login`.
Lines read
1,332
File checksum (to compare versions)
e4e312e2988a5ed185c718ba19c6595ee4579ddfd4d46dcd6d192f35de3e09d9