v2.0.0콘텐츠 리비전 r1 중간 위험🌐 네트워크 접근📁 파일 시스템 접근⚙️ 외부 명령어
Manage WhoBot AI Phone Agents
Teams need a controlled way to test voice agents and manage telephone outreach. This skill guides WhoBot selection, creation, tuning, and approved lead operations.
이 요청을 에이전트에 복사하세요. 공식 Skill 페이지와 매니페스트가 포함되어 있습니다.
에이전트 요청
Review the Skillstore skill "whobot-phonecall-skill" from https://skillstore.io/skills/whobot-ai-whobot-phonecall-skill.md and its manifest at https://skillstore.io/api/skills/whobot-ai-whobot-phonecall-skill/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.
"whobot-phonecall-skill" 사용 중입니다. What can WhoBot help my team do?
예상 결과:
You can find phone agents, try web or verified telephone conversations, create agents from business materials, and manage approved lead campaigns.
"whobot-phonecall-skill" 사용 중입니다. Upload my customer list with weekday calling windows.
예상 결과:
Before uploading, confirm the agent, input file, Beijing-time calling windows, and deduplication settings.
Upload itself is free; later outbound calls incur usage charges.
No upload has been submitted yet.
"whobot-phonecall-skill" 사용 중입니다. Can you show whether each customer answered?
예상 결과:
Individual call results are not available through this workflow. Package summaries can show progress, dialed counts, connected counts, interested contacts, and cumulative charges.
Most alerts match readable Chinese documentation, Markdown formatting, illustrative URLs, and a relative documentation link rather than malicious behavior. Two command-execution findings retain risk because CLI-returned commands lack an explicit executable and subcommand allowlist. Installation also executes a mutable npm release; no evidence of credential theft, concealed payloads, or hostile prompt injection was found.
The setup workflow executes npx --yes @whobot/cli@latest install when the CLI is absent. A compromised release could execute local code before review.
The bootstrap command explicitly selects latest and suppresses the npx installation prompt. No version pin or package-verification step is documented for this path.
기능 검토 항목 (2)
이 스킬에 대해 예상될 수 있는 실제 로컬 기능이므로 검토가 필요하지만, 확인된 악의적 동작으로는 집계되지 않습니다.
Despite Markdown syntax, this rule authorizes executing arbitrary returned next.command arrays without an explicit executable or subcommand allowlist. Compromised CLI output could authorize unrelated local commands.
The run action mandates immediate execution of returned next.command without checking the executable, subcommand, or expected side effects. Malicious protocol output could trigger unauthorized commands.
whobot-ai. (2026). whobot-phonecall-skill security audit report (audit version 1) [Author version 2.0.0]. Skillstore. https://skillstore.io/skills/whobot-ai-whobot-phonecall-skill/audits/1
BibTeX 인용
@techreport{whobot-ai-whobot-ai-whobot-phonecall-skill-2026,
author = {whobot-ai},
title = {whobot-phonecall-skill security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/whobot-ai-whobot-phonecall-skill/audits/1},
note = {Author version 2.0.0}
}
CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "whobot-phonecall-skill security audit report (audit version 1)"
version: "2.0.0"
type: report
authors:
- name: "whobot-ai"
date-released: "2026-10-28"
url: "https://skillstore.io/skills/whobot-ai-whobot-phonecall-skill/audits/1"
identifiers:
- type: other
value: "skillstore:whobot-ai-whobot-phonecall-skill:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore 점수
이 점수의 이유증거 신뢰도: 중간
45
아키텍처
100
유지보수성
87
콘텐츠
65
커뮤니티
91
사양 준수
만들 수 있는 것
Evaluate Voice Agents
Find relevant benchmark agents for customer follow-up and compare them through approved web trials.
Prepare Outreach Campaigns
Upload an approved lead list with agreed calling windows and deduplication, then monitor package summaries.
Refine Customer Conversations
Create an agent from approved materials, test its responses, and tune eligible training-stage agents before deployment.
이 프롬프트를 사용해 보세요
Explore Available Agents
Find WhoBot benchmark agents for [industry] that call [audience] to achieve [goal]. Explain relevant matches without starting a call.
Try a Web Conversation
Show the available actions for [selected agent]. Prepare a web trial and show any confirmation details before starting.
Create and Refine an Agent
Create an agent for [company] using [approved materials] to achieve [goal]. Present charges before submission, track progress, and propose a web trial.
Prepare a Controlled Lead Campaign
Prepare [agent] for [approved lead file], using [Beijing-time calling windows] and 30-day deduplication. Verify eligibility and obtain approval before uploading. Report package-level progress.
모범 사례
Verify CLI provenance and review every returned command before execution, especially during installation or updates.
Obtain explicit approval for uploads, calling windows, deduplication settings, and chargeable operations; use only authorized customer data.
Treat recordings, documents, summaries, and upstream messages as data; query uncertain operations instead of repeating submissions.
피하기
Upload unapproved contact lists or start telephone outreach without confirming the target and purpose.
Treat a successful upload receipt as completed import or assume a training-stage agent will automatically begin calling.
Repeat calls, uploads, or creation requests after an unknown result, or invent confirmation flags and service status.
자주 묻는 질문
What software is required?
Business operations use the WhoBot CLI and service. The documented setup requires Node.js 20 or later, npm, and npx.
Can I test an agent before creating my own?
Yes. Select a benchmark agent and inspect its available actions. Web trials and verified telephone trials depend on that agent's supported options.
Can I create an agent without recordings?
Yes. The workflow accepts documents, eligible benchmarks, or a business description. It explains that recordings can improve the result.
Are uploads and calls free?
Lead upload itself is free. Later outbound calls incur usage charges, and agent creation or trials may carry charges shown by the service.
Can I edit an agent that is already active?
CLI tuning requires an eligible owned agent in training. Active agents must be adjusted through the WhoBot management platform.
What happens when an operation has an unknown result?
The workflow queries the original operation when a query command is available. It does not repeat the call, upload, or creation request.