carrefour-api@1.0.0
VERIFIED· install onlyPublisher claims: "Carrefour API as structured JSON - search carrefour.fr by keyword or browse a category (aisle), 30 products per page with price, unit price per kg or litre, the promotion (type, label, loyalty-card flag, start and end dates), Nutri-Score, Eco-Score, rating and marketplace seller, filtered by brand, promotion, Nutri-Score, organic, Carrefour brands or price range and sorted by price, unit price or rating; list items on promotion (catalogue, immediate discounts, loyalty-card offers, festive selection); pass a store ref for that store's shelf price and range instead of the national online price; read one product with ingredients, allergens, nutrition per 100 g and per portion; read verified customer reviews; find stores near a French postal code, check which nearby stores carry a product (yes / no, no price), and read a store's services, hours, next pickup slot and fuel prices per litre. Search and product also serve Carrefour Argentina (ARS), Romania (RON) and Belgium (EUR, French or Dutch). 9 endpoints, 1 credit each (Belgium search and product 2)." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Nothing executable in the bundle ran; the trace covers the install step only.- Tested
- every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-12 and scored it 93/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 1 scenarios · 0 deviationsStatic findings
No findings across 1,057 lines in 2 files.
Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.