스킬 yelp
📦
yelp
콘텐츠 리비전 r1 중간 위험 ⚙️ 외부 명령어🌐 네트워크 접근📁 파일 시스템 접근🔑 환경 변수
Search Yelp Businesses and Reviews
Local business research requires searching listings and gathering details and reviews. This skill documents paid fetcher.sh requests for these tasks through HTTP and MCP.
지원: Claude Codex Code(CC)
내 에이전트로 설치
이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.
에이전트 요청
Review the Skillstore skill "yelp" from https://skillstore.io/skills/fetcher-sh-yelp.md and its manifest at https://skillstore.io/api/skills/fetcher-sh-yelp/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.에이전트는 계속해서 계획을 표시하고 보안 정책에서 요구하는 확인을 요청해야 합니다.
에이전트가 읽기 쉬운 리소스
AI 에이전트, 크롤러, 스크립트가 전체 페이지 대신 정리된 컨텍스트만 필요할 때 이 링크를 사용하세요.
테스트해 보기
"yelp" 사용 중입니다. Explain the request for ramen businesses in San Francisco sorted by rating.
예상 결과:
- Search: ramen in San Francisco.
- Sorting: rating.
- Endpoint: business search.
- Documented cost: $0.003 for one call.
- Payment approval is required before execution.
"yelp" 사용 중입니다. Explain how to retrieve a business's second review page.
예상 결과:
- Use the business ID with the reviews endpoint.
- Set the page parameter to 2.
- Authenticate with prepaid credits or an approved x402 payment setup.
- Stop after payment errors; upstream failures may still incur charges.
"yelp" 사용 중입니다. Which documented MCP tools are free or paid?
예상 결과:
- Free: search_endpoints, describe_endpoint, and check_balance.
- Paid: fetch_data, topup_credits, and yelp_search.
- Confirm spending and credit topups before invoking paid tools.
보안 감사
중간 위험v1 • 2026. 9. 30. 버전별 보고서 열기
All 57 static findings are false positives involving Markdown, reference links, documented API calls, placeholders, or expected service authentication. No evidence found of malware, credential theft, or prompt injection in the reviewed file. A separate payment-safety finding concerns automatic signing without documented spending limits and nonrefundable upstream failures.
1
스캔된 파일
138
분석된 줄 수
0
검토 항목
0
오탐 무시됨
확인된 보안 우려 사항 (1)
중간
Automatic payments lack documented spending safeguards
The guide says payment signing and retries are automatic and exposes paid MCP tools without spending limits or confirmation requirements. Nonrefundable upstream failures can amplify losses from repeated agent calls.
Automatic signing, paid tools, and nonrefundable settlement are explicit; this file supplies no consent or budget controls. External implementations may impose safeguards, but were not reviewed.
위험 요인
⚙️ 외부 명령어 (30)
SKILL.md:29 SKILL.md:33 SKILL.md:36-46 SKILL.md:46-48 SKILL.md:48-49 SKILL.md:49-55 SKILL.md:55-56 SKILL.md:56-57 SKILL.md:57-58 SKILL.md:58-60 SKILL.md:60 SKILL.md:61 SKILL.md:67-73 SKILL.md:73-77 SKILL.md:77-83 SKILL.md:83-87 SKILL.md:87-93 SKILL.md:93-97 SKILL.md:97-101 SKILL.md:101-105 SKILL.md:105-114 SKILL.md:114-116 SKILL.md:116 SKILL.md:117 SKILL.md:118 SKILL.md:119-123 SKILL.md:123-124 SKILL.md:124-125 SKILL.md:125 SKILL.md:127-136
🌐 네트워크 접근 (13)
📁 파일 시스템 접근 (3)
감사자: codex
이 보고서 공유 및 인용
버전이 지정된 평가 보고서, 중립 배지, 임베드 카드 및 인용을 공유하세요. Skillstore는 근거를 보고하지만 이 Skill의 안전 여부를 판단하지 않습니다.
보고서 링크 복사
https://skillstore.io/skills/fetcher-sh-yelp/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 배지
[](https://skillstore.io/skills/fetcher-sh-yelp?utm_source=security_passport_badge)HTML 배지
<a href="https://skillstore.io/skills/fetcher-sh-yelp?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/fetcher-sh-yelp/security.svg" alt="Skillstore security assessment" loading="lazy"></a>임베드 카드
<iframe src="https://skillstore.io/embed/skills/fetcher-sh-yelp.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>학술 인용 (APA · BibTeX · CFF)
APA 인용
fetcher-sh. (2026). yelp security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/fetcher-sh-yelp/audits/1BibTeX 인용
@techreport{fetcher-sh-fetcher-sh-yelp-2026,
author = {fetcher-sh},
title = {yelp security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/fetcher-sh-yelp/audits/1},
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: "yelp security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "fetcher-sh"
date-released: "2026-09-30"
url: "https://skillstore.io/skills/fetcher-sh-yelp/audits/1"
identifiers:
- type: other
value: "skillstore:fetcher-sh-yelp:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore 점수
이 점수의 이유 증거 신뢰도: 중간 55
아키텍처
85
유지보수성
87
콘텐츠
65
커뮤니티
83
사양 준수
만들 수 있는 것
Compare dining options
Search restaurants in a destination and compare returned results by rating or review count.
Research local competitors
Find nearby businesses and retrieve their details and review pages for manual comparison.
Connect a research assistant
Configure the remote MCP service and use its documented tools within an approved request budget.
이 프롬프트를 사용해 보세요
Search a location
Find ramen businesses in San Francisco using fetcher.sh. Confirm the payment method and one-call cost before making the request.
Compare search sorting
Search tacos in Austin by rating, then by review count. Ask approval for two paid calls and compare only returned results.
Retrieve details and reviews
Retrieve details and review page two for Yelp handle gary-danko-san-francisco. Confirm a two-call budget and stop on payment errors.
Plan an MCP workflow
Plan a Yelp MCP workflow for competitor research. Separate free discovery from paid retrieval, protect credentials, and require approval for spending and topups.
모범 사례
- Verify current pricing and authorize a request budget before paid calls or credit topups.
- Keep service keys outside prompts and shared configuration; send them only to the intended provider.
- Use explicit locations, supported sort values, and limited pagination; stop after paid failures.
피하기
- Allowing automatic paid retries or credit topups without spending approval.
- Placing live Bearer keys in shared files, chat messages, or logs.
- Treating returned reviews as complete, current, or statistically representative without verification.
자주 묻는 질문
Is this the official Yelp Fusion API?
No. It documents a third-party fetcher.sh service for Yelp business data, not a direct Yelp Fusion integration.
How are requests paid?
The guide supports prepaid credits with a Bearer key or per-call USDC payments through x402.
What does a request cost?
The guide lists $0.003 per call for its four data endpoints. Verify current prices before approving requests.
Can I sort and paginate results?
Search supports recommendation, rating, and review-count sorting plus pagination. Review retrieval also supports a page parameter.
Can Claude, Codex, and Claude Code use this skill?
The skill provides HTTP instructions and remote MCP configuration. Execution depends on the client's tools, connectivity, credentials, and payment setup.
Are failed requests refunded?
The guide states that upstream failures are nonrefundable because settlement precedes delivery. Approve budgets and avoid uncontrolled retries.
개발자 세부 정보
작성자
fetcher-sh라이선스
MIT
Skillstore 리비전
r1
버전 안내
작성자가 버전을 선언하지 않았습니다.
참조
d47538c68dbdc71b7d5879e2b0a19d3608869cea
유지보수 최신성
2026. 9. 30.
사용량
0 다운로드 · 0 조회
파일 구조
📄 SKILL.md