Skills amazon-product-api-skill
📦
amazon-product-api-skill
Content revision r2 Safe 🌐 Network access🔑 Env variables⚙️ External commands
Search Amazon Products with BrowserAct
Manual Amazon product research is slow and inconsistent. This skill submits BrowserAct workflows and monitors their status for structured listing data.
Supports: Claude Codex Code(CC)
This skill is part of a pack
Install the whole pack to get every skill the task needs, in one command.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Agent request
Review the Skillstore skill "amazon-product-api-skill" from https://skillstore.io/skills/browser-act-amazon-product-api-skill.md and its manifest at https://skillstore.io/api/skills/browser-act-amazon-product-api-skill/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "amazon-product-api-skill". Search for Samsung wireless earbuds on one English results page.
Expected outcome:
- Matching products are listed with title, ASIN, product URL, and brand.
- Each available listing includes current price, original price, average rating, and rating count.
- Featured badges and available color, material, or style details appear beside each product.
Using "amazon-product-api-skill". Compare Dell laptop listings across two German results pages.
Expected outcome:
The report groups Dell listings by price and rating, highlights featured products, and notes unavailable specifications.
Security Audit
Safev6 • 7/23/2026 Open versioned report
Most static alerts are false positives caused by Markdown backticks, normal error checks, or standard bearer-token handling. The skill makes intentional BrowserAct network requests, but its instructions to provide an API key in chat create a high-risk credential exposure path.
2
Files scanned
218
Lines analyzed
7
Review items
0
False positives ignored
Capability review items (7)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
High
Generic API/secret keys
print("3. Set it as an environment variable (BROWSERACT_API_KEY) or provide it in the chat.", flush=
The message explicitly permits providing an API key in chat. Credentials entered into a conversation can be retained in transcripts or exposed to unintended processors.
High
Generic API/secret keys
Before running, check the `BROWSERACT_API_KEY` environment variable. If not set, do not take other m
The instruction tells the agent to ask the user to provide the API key when the environment variable is absent. This encourages disclosure of a credential into chat history.
Low
Python HTTP libraries
response = requests.post(f"{API_BASE_URL}/run-task-by-template", json=payload, headers=headers, time
This POST sends user search parameters and a bearer credential to the external BrowserAct API. The transfer is expected for the skill, but it creates a real third-party network trust boundary.
Low
Python HTTP libraries
status_res = requests.get(f"{API_BASE_URL}/get-task-status?task_id={task_id}", headers=headers, time
This GET polls the external BrowserAct API with the bearer credential and task identifier. It is intentional but remains a real outbound network operation.
Low
Hardcoded URL
API_BASE_URL = "https://api.browseract.com/v2/workflow"
This fixed URL defines the external BrowserAct destination used for authenticated requests. It is a legitimate service endpoint, but it establishes the network destination receiving user parameters.
Low
Python getenv function
api_key = os.getenv("BROWSERACT_API_KEY")
The script reads BROWSERACT_API_KEY from the process environment. Access is narrow and expected, but it is real access to credential-bearing environment data.
Low
getenv function call
api_key = os.getenv("BROWSERACT_API_KEY")
The getenv call retrieves the BrowserAct credential from the environment. It does not enumerate unrelated variables, so the confirmed risk is limited to expected secret access.
Risk Factors
🌐 Network access (6)
🔑 Env variables (10)
⚙️ External commands (26)
SKILL.md:20 SKILL.md:28 SKILL.md:31 SKILL.md:34 SKILL.md:36 SKILL.md:37 SKILL.md:40 SKILL.md:42 SKILL.md:45 SKILL.md:47 SKILL.md:48 SKILL.md:53-56 SKILL.md:56-59 SKILL.md:59-67 SKILL.md:67-68 SKILL.md:68-69 SKILL.md:69-70 SKILL.md:70-71 SKILL.md:71-72 SKILL.md:72-73 SKILL.md:73-74 SKILL.md:74-75 SKILL.md:75-76 SKILL.md:76 SKILL.md:82-83 SKILL.md:83
Audited by: codex View Audit History →
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/browser-act-amazon-product-api-skill/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/browser-act-amazon-product-api-skill?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/browser-act-amazon-product-api-skill?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/browser-act-amazon-product-api-skill/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/browser-act-amazon-product-api-skill.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
browser-act. (2026). amazon-product-api-skill security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/browser-act-amazon-product-api-skill/audits/6BibTeX citation
@techreport{browser-act-browser-act-amazon-product-api-skill-2026,
author = {browser-act},
title = {amazon-product-api-skill security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/browser-act-amazon-product-api-skill/audits/6},
note = {Author version unspecified}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "amazon-product-api-skill security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "browser-act"
date-released: "2026-07-23"
url: "https://skillstore.io/skills/browser-act-amazon-product-api-skill/audits/6"
identifiers:
- type: other
value: "skillstore:browser-act-amazon-product-api-skill:audit:6"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: High 45
Architecture
85
Maintainability
87
Content
68
Community
83
Spec Compliance
What You Can Build
Compare Market Listings
Collect product titles, prices, ratings, and featured badges for a keyword and brand.
Enrich Product Catalogs
Gather ASINs, product URLs, brands, and available attributes for catalog review.
Research Localized Results
Run searches with different interface languages to examine localized product listings.
Try These Prompts
Search One Product Category
Search Amazon for wireless earbuds from Samsung using one page and English. Summarize titles, ASINs, prices, and ratings.
Compare Listing Quality
Search Amazon for Dell laptops across two pages in German. Compare current prices, original prices, ratings, rating counts, and featured badges.
Evaluate Product Attributes
Find one page of Logitech wireless mouse listings in English. Group results by material, color, and style, and identify missing attributes.
Compare Two Brands
Run separate one-page searches for Apple and Samsung tablets in English. Compare median prices, rating strength, featured badges, and listing coverage.
Best Practices
- Set BROWSERACT_API_KEY through an approved environment or secret-management tool.
- Start with one page, then expand only when the initial query is relevant.
- Record query parameters and collection time when comparing separate runs.
Avoid
- Do not paste API keys into chat, prompts, logs, or command arguments.
- Do not treat current listing prices as historical price-change evidence.
- Do not request many pages before confirming the keyword and brand filters.
Frequently Asked Questions
What credentials does this skill require?
It requires a BrowserAct API key provided through the BROWSERACT_API_KEY environment variable.
Does the skill call Amazon directly?
No. It submits a fixed Amazon product workflow to BrowserAct, which performs the browser task.
Which search options are supported?
The script accepts keywords, one brand, a page count, and an interface language.
How long can a search run?
The script polls every ten seconds and stops after five minutes.
Can it track price history automatically?
No. It does not store prior results or calculate changes between collection times.
Why might no product data appear?
The current control flow returns after polling before result retrieval. The script requires a code fix to print completed task data.
Developer Details
Author
browser-actLicense
MIT
Skillstore revision
r2
Version notice
The author did not declare a version.
Repository
https://github.com/browser-act/skills/tree/main/solutions/ecommerce/amazon-product-api-skillRef
a39a91716eadede5f4cdefd78178fed4e837a128
Maintenance freshness
7/24/2026
Usage
11 downloads · 84 views
File structure