detect-ai
Detect AI-Written Text
AI-generated text can be hard to identify before submission or publication. This skill sends text to HumanizerAI and returns a clear score, metrics, and recommendation.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "detect-ai" from https://skillstore.io/skills/humanizerai-detect-ai.md and its manifest at https://skillstore.io/api/skills/humanizerai-detect-ai/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 "detect-ai". A short product description that sounds polished and repetitive.
Expected outcome:
AI Detection Results: Score 78 out of 100, likely AI-generated. The recommendation is to revise sentence variety and add specific human context.
Using "detect-ai". A personal essay draft with uneven sentence length and concrete details.
Expected outcome:
AI Detection Results: Score 24 out of 100, likely human-written. The recommendation is to keep the natural structure and review only for clarity.
Using "detect-ai". A mixed report section combining original notes with generated summary text.
Expected outcome:
AI Detection Results: Score 55 out of 100, mixed signals. The recommendation is to inspect high-scoring sections and rewrite generic passages.
Security Audit
Medium RiskMost external command findings are false positives caused by Markdown backticks and fenced examples, not executable shell code. The meaningful risk is intentional submission of user text to the HumanizerAI API. No hardcoded secret or prompt injection language was found.
Confirmed security concerns (1)
Capability review items (1)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚙️ External commands (8)
🌐 Network access (2)
🔑 Env variables (2)
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/humanizerai-detect-ai/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/humanizerai-detect-ai?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/humanizerai-detect-ai?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/humanizerai-detect-ai/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/humanizerai-detect-ai.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
humanizerai. (2026). detect-ai security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/humanizerai-detect-ai/audits/6BibTeX citation
@techreport{humanizerai-humanizerai-detect-ai-2026,
author = {humanizerai},
title = {detect-ai security audit report (audit version 6)},
institution = {Skillstore},
year = {2026},
number = {6},
url = {https://skillstore.io/skills/humanizerai-detect-ai/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: "detect-ai security audit report (audit version 6)"
version: "unspecified"
type: report
authors:
- name: "humanizerai"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/humanizerai-detect-ai/audits/6"
identifiers:
- type: other
value: "skillstore:humanizerai-detect-ai:audit:6"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Review Publication Drafts
Screen articles, posts, and web copy before release to identify AI-writing signals.
Check Academic Drafts
Review essays or research summaries for AI-like patterns before sharing or submitting them.
Assess Vendor Copy
Evaluate submitted marketing text when policies require disclosure of AI-assisted writing.
Try These Prompts
/detect-ai Please analyze this paragraph: [paste text]
/detect-ai Analyze this full draft for AI-writing signals. Focus on the overall score and strongest metrics: [paste draft]
/detect-ai Analyze this revised text and tell me whether it still appears AI-generated: [paste revised text]
/detect-ai Analyze this publication draft. Summarize the score, metrics, and risk of submitting it as human-written: [paste draft]
Best Practices
- Remove private or regulated information before running detection.
- Treat the score as a review signal, not a final judgment.
- Check the overall score together with metric patterns and context.
Avoid
- Do not submit confidential customer, employee, or legal text without approval.
- Do not accuse an author based only on one score.
- Do not expose the API key in prompts, screenshots, or logs.
Frequently Asked Questions
What does this skill analyze?
Does it send text outside my workspace?
Do I need an API key?
Is the score proof that text was AI-written?
Which score should I trust first?
Does it work with Claude, Codex, and Claude Code?
Developer Details
Author
humanizeraiLicense
MIT
Skillstore revision
r1
Version notice
The author did not declare a version.
Ref
0519034dad657fb1f7706e0550e962beeda73fdf
Maintenance freshness
7/18/2026
Usage
27 downloads · 205 views
File structure
📄 SKILL.md