Product to Ads (Ad-Ready)
v1.4.0Generate professional advertising images from product URLs using the Ad-Ready pipeline on ComfyDeploy. Use when the user wants to create ads for any product by providing a URL, optionally with a brand profile (70+ brands) and funnel stage targeting. Supports model/talent integration, brand-aware creative direction, and multi-format output. Differs from Morpheus (manual fashion photography) — Ad-Ready is URL-driven, brand-intelligent, and funnel-stage aware.
⭐ 1· 1.6k·1 current·1 all-time
byPaul de Lavallaz@pauldelavallaz
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
The skill claims to produce ads from product URLs (expected). However, the SKILL.md and files reference local model/talent catalogs (~/clawd/models-catalog/...), ComfyDeploy/ComfyUI nodes, and external models (Gemini Flash, Nano Banana Pro, Imagen 3) that typically require credentials or local assets. None of those credentials, config paths, or binaries are declared in the metadata, creating a mismatch between stated purpose and required resources.
Instruction Scope
Runtime instructions explicitly direct scraping arbitrary product pages (downloading high-res images and logos) and optionally reading a local models-catalog path. They also describe sending data into multi-phase pipelines that use external models/services. The instructions therefore include web scraping, network requests, and local filesystem access beyond what the skill metadata declares.
Install Mechanism
No install spec is provided (instruction-only install), which limits automatic code installation risk. However, a non-trivial Python script (scripts/generate.py) is included in the bundle — there's code to run but no declared install/run instructions or dependency list. That inconsistency means reviewers should inspect the script to understand what it does and what it will call or require.
Credentials
The skill declares no required environment variables or config paths, yet the SKILL.md implies reliance on external APIs/models and local catalogs. Typical integrations with Gemini/Imagen/ComfyDeploy would need credentials or local model files. Also referencing a hardcoded user-home path (~/.clawd/...) without declaring it is disproportionate and potentially invasive.
Persistence & Privilege
The skill does not set always:true, but it also does not set disableModelInvocation:true. That means the model could autonomously invoke this skill. Combined with instructions that read local paths and make network calls, that increases risk because the skill could be triggered without an explicit user action and access local assets or external endpoints.
What to consider before installing
Before installing, inspect the included scripts (scripts/generate.py) to see exactly what network calls, APIs, and filesystem paths are used. Confirm whether the skill requires API keys for Gemini/Imagen/ComfyDeploy or other services; the metadata currently declares none. Be wary that SKILL.md references reading ~/clawd/models-catalog and downloading product images/logos from arbitrary URLs — if you don't want local files exposed, do not grant filesystem access or run this skill in an isolated sandbox. Ask the publisher for a homepage/source-of-truth (the SKILL.md points at a GitHub repo but the registry lists 'source: unknown'). Consider requiring explicit user invocation only (set disableModelInvocation=true) until you can verify the code and credential needs. Finally, validate licensing/privacy implications of scraping product pages and using brand assets or model likenesses for ads.Like a lobster shell, security has layers — review code before you run it.
latestvk97a59cr7mdw1ex3h64mft7w7n80j42c
License
MIT-0
Free to use, modify, and redistribute. No attribution required.