webask-data-quality
Check WebAsk Survey Data Quality
Suspicious survey responses can distort results and weaken decisions. This skill guides checks of WebAsk responses and compares key metrics before recommending exclusions.
使用我的智慧代理安裝
將此請求複製給你的智慧代理，其中包含權威 Skill 頁面和清單。
Review the Skillstore skill "webask-data-quality" from https://skillstore.io/skills/webaskio-webask-data-quality.md and its manifest at https://skillstore.io/api/skills/webaskio-webask-data-quality/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.你的智慧代理仍應顯示其計畫，並依安全政策請求必要確認。
Agent 可讀資源
當 AI Agent、爬蟲或腳本需要乾淨脈絡、而不是讀取完整頁面時，請使用這些連結。
測試它
正在使用「webask-data-quality」。 Illustrative request: Review 100 responses and estimate the effect of excluding suspicious submissions.
預期結果:
- Fast completions: 12 responses, or 12%. Repetitive choices: 8 responses, or 8%.
- Four responses match both indicators. Unique flagged responses: 16, or 16%.
- Excluding those responses would leave 84. The average rating would change from 4.0 to 4.1.
- Recommend reviewing and tagging flagged responses before deciding on exclusions. No responses were changed.
正在使用「webask-data-quality」。 Illustrative request: Review contradictory answers and harsh comments before publishing survey results.
預期結果:
- Three responses deny using the service but also rate its quality. Review the survey display logic.
- Five comments contain specific complaints. Negative sentiment alone is not a reason to exclude them.
- Recommend reviewing contradictions separately from critical feedback. No responses were changed.
安全審計
安全All three static findings are false positives: relative documentation links and Markdown formatting around tool names. No evidence found of prompt injection, unauthorized execution, or data exfiltration in the reviewed files. The workflow uses survey retrieval tools and prohibits autonomous deletion.
風險因素
📁 檔案系統存取 (1)
⚙️ 外部命令 (2)
分享與引用此報告
分享版本化評估報告、中性徽章、嵌入卡片與引用。Skillstore 只報告證據，不判斷該 Skill 是否安全。
複製報告連結
https://skillstore.io/skills/webaskio-webask-data-quality/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown 徽章
[](https://skillstore.io/skills/webaskio-webask-data-quality?utm_source=security_passport_badge)HTML 徽章
<a href="https://skillstore.io/skills/webaskio-webask-data-quality?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/webaskio-webask-data-quality/security.svg" alt="Skillstore security assessment" loading="lazy"></a>嵌入卡片
<iframe src="https://skillstore.io/embed/skills/webaskio-webask-data-quality.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>學術引用 (APA · BibTeX · CFF)
APA 引用
webaskio. (2026). webask-data-quality security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/webaskio-webask-data-quality/audits/1BibTeX 引用
@techreport{webaskio-webaskio-webask-data-quality-2026,
author = {webaskio},
title = {webask-data-quality security audit report (audit version 1)},
institution = {Skillstore},
year = {2026},
number = {1},
url = {https://skillstore.io/skills/webaskio-webask-data-quality/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: "webask-data-quality security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
- name: "webaskio"
date-released: "2026-09-29"
url: "https://skillstore.io/skills/webaskio-webask-data-quality/audits/1"
identifiers:
- type: other
value: "skillstore:webaskio-webask-data-quality:audit:1"
description: "Skillstore immutable audit report identifier"
Skillstore 評分
評分依據 證據置信度: 中你可以打造什麼
Review an incentivized survey
Inspect fast completions, repeated contacts, and matching response bursts before interpreting results from a rewarded survey.
Prepare a survey report
Compare key metrics before and after proposed exclusions to assess whether quality concerns affect the report.
Investigate conflicting feedback
Review contradictory responses and possible survey display logic errors without treating negative customer feedback as invalid.
試試這些提示
Check the response quality for WebAsk survey [survey]. Summarize the main concerns without changing any responses.
Review [survey] for fast completions, repetitive answers, duplicate contacts, and meaningless text. Report counts and percentages for each indicator.
For [survey], compare [key metrics] before and after proposed exclusions. Count overlapping flags only once when calculating remaining responses. Do not modify data.
Investigate matching response bursts, duplicate contacts, and contradictory answers in [survey]. Separate possible display logic errors from suspicious behavior. Compare metric changes and recommend reversible actions.
最佳實務
- Review suspicious indicators in context before treating any response as invalid.
- Report indicator percentages and count overlapping flags only once when estimating remaining responses.
- Compare key metrics before exclusions and prefer reversible tagging.
避免
- Removing low ratings or harsh comments solely because they are negative.
- Deleting flagged responses without an explicit request and confirmation.
- Changing the sample to produce a preferred conclusion.
常見問題
Which AI tools are supported?
What WebAsk tools does it require?
Does a suspicious response prove fraud?
Will it automatically delete responses?
Does it exclude negative feedback?
What happens when a service limit is reached?
開發者詳細資訊
作者
webaskio授權
MIT
Skillstore 修訂
r1
版本提示
作者未聲明版本。
引用
bad9dafc37d1638cd29cb9bab06d5f8dbcd0f6c2
維護新鮮度
2026/9/30
使用量
0 次下載 · 0 次瀏覽
檔案結構