Ad-Ready
PassAudited by ClawScan on May 1, 2026.
Overview
The skill appears coherent for generating ad images, with the main user considerations being product-page scraping and external AI processing of product/reference images.
This looks suitable for its advertised purpose if you are comfortable with automated product-page scraping and external AI image generation. Use public product URLs, avoid sensitive campaign assets unless approved for provider processing, and ensure you have rights or consent for any product, brand, reference, or model images used.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A product page URL you provide may be requested, parsed, and used to download product images.
The skill is designed to fetch and parse user-provided product pages and download product imagery. This is core to the stated purpose, but users should ensure the URL is intended for automated access.
PHASE 1: Product Scraping (Gemini Flash) ... Scrapes product URL → extracts title, description, features, price, materials, image URLs ... Also scrapes HTML for high-res product images
Use public product URLs you are authorized to process, and avoid private, internal, or sensitive links.
Product details, brand direction, and any provided reference or talent images may leave the local agent environment for generation.
The artifacts disclose that campaign data and reference imagery are processed through external AI/provider infrastructure. This is expected for the skill, but users should treat product, brand, and talent/reference images as data shared with those services.
The pipeline runs as a ComfyUI custom node deployed on ComfyDeploy ... PHASE 4: Image Generation (Nano Banana Pro / Imagen 3) ... Blueprint + all reference images → final ad image
Only provide assets you are allowed to share with external AI services, and obtain consent for any identifiable person used as a model/reference.
It may be harder to independently confirm that the installed package matches the claimed upstream source.
Registry-level provenance is sparse, even though the SKILL.md content names a GitHub source. This is not evidence of malicious behavior, but it is a provenance detail users should verify if they rely on the packaged script/configuration.
Source: unknown; Homepage: none
Prefer installing from trusted registry entries and compare the package with the claimed source if provenance matters for your workflow.