Skills humanize
📦

humanize

Content revision r1 High Risk ⚙️ External commands🌐 Network access🔑 Env variables

Rewrite Text with HumanizerAI

AI-style drafts can sound stiff and repetitive. This skill rewrites supplied text through HumanizerAI and returns score, word, and credit details.

Supports: Claude Codex Code(CC)
⚠️ 38 Poor

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "humanize" from https://skillstore.io/skills/humanizerai-humanize.md and its manifest at https://skillstore.io/api/skills/humanizerai-humanize/manifest. Verify the artifact. Stop and obtain explicit user consent before installing or changing files.

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.

Markdown detail GET /skills/humanizerai-humanize.md Signed manifest GET /api/skills/humanizerai-humanize/manifest Signed lockfile GET /api/skills/humanizerai-humanize/lockfile

Test it

Using "humanize". A product paragraph asks users to configure access before the platform can operate.

Expected outcome:

The skill returns a smoother paragraph, reports the score change, lists words processed, and shows remaining credits.

Using "humanize". A support email sounds stiff and repetitive.

Expected outcome:

The skill returns a friendlier version and suggests light intensity when only small changes are needed.

Using "humanize". A technical explanation needs clearer wording without changing steps.

Expected outcome:

The skill rewrites the paragraph and keeps important terms, sequence, and operational details visible.

Security Audit

High Risk
v4 • 7/6/2026 Open versioned report

Most shell-execution findings are false positives from Markdown backticks and fenced examples. Confirmed risks remain for the external HumanizerAI API request and use of HUMANIZERAI_API_KEY. The skill also presents a high-confidence detector-evasion and authorship-risk use case.

1
Files scanned
92
Lines analyzed
3
Review items
0
False positives ignored

Confirmed security concerns (2)

High
SKILL.md:3SKILL.md:36
Detector Evasion and Authorship Misrepresentation Risk
The skill advertises bypassing GPTZero, Turnitin, and Originality.ai, and labels aggressive mode as maximum bypass. This can support policy evasion and misrepresented authorship.
The bypass claim is explicit in the skill metadata and intensity table. The named detectors include Turnitin, which strongly indicates academic-integrity evasion risk.
Medium
SKILL.md:17-19SKILL.md:40-49
External Processing of User Text Without Consent Step
The workflow sends the user text to HumanizerAI without requiring consent or warning against sensitive data. This can expose private drafts to a third party.
The workflow explicitly parses user text and calls the external API. The file contains no consent, privacy, or sensitive-data warning before transmission.
Capability review items (3)

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
SKILL.md:43
Generic API/secret keys
Authorization: Bearer $HUMANIZERAI_API_KEY
The Authorization header uses HUMANIZERAI_API_KEY from the environment and sends it to an external API. This is expected credential use but still creates secret-handling risk.
High
SKILL.md:87
Generic API/secret keys
1. Check HUMANIZERAI_API_KEY environment variable
The skill instructs checking the HUMANIZERAI_API_KEY environment variable during errors. This can lead an agent to inspect secret-bearing environment data.
Medium
SKILL.md:40
Hardcoded URL
Make a POST request to `https://humanizerai.com/api/v1/humanize`:
Line 40 instructs the agent to POST user-supplied text to a fixed external HumanizerAI API. This is intentional network egress and creates a privacy dependency.

Risk Factors

⚙️ External commands (11)
SKILL.md:15 SKILL.md:25 SKILL.md:26 SKILL.md:28 SKILL.md:34 SKILL.md:35 SKILL.md:36 SKILL.md:40 SKILL.md:42-50 SKILL.md:50-56 SKILL.md:56-71
🌐 Network access (4)
SKILL.md:40 SKILL.md:77 SKILL.md:84 SKILL.md:88
🔑 Env variables (2)
SKILL.md:43 SKILL.md:87
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.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/humanizerai-humanize/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/humanizerai-humanize/security.svg)](https://skillstore.io/skills/humanizerai-humanize?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/humanizerai-humanize?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/humanizerai-humanize/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/humanizerai-humanize.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). humanize security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/humanizerai-humanize/audits/4

BibTeX citation

@techreport{humanizerai-humanizerai-humanize-2026, author = {humanizerai}, title = {humanize security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/humanizerai-humanize/audits/4}, 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: "humanize security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "humanizerai" date-released: "2026-07-06" url: "https://skillstore.io/skills/humanizerai-humanize/audits/4" identifiers: - type: other value: "skillstore:humanizerai-humanize:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
71
Community
83
Spec Compliance

What You Can Build

Polish Marketing Drafts

Rewrite campaign copy so it sounds smoother while preserving the core offer and product details.

Improve Support Replies

Turn stiff service responses into clear, friendly replies before sending them to customers.

Refine Documentation Text

Make explanatory paragraphs easier to read while keeping technical terms and steps intact.

Try These Prompts

Humanize a Short Paragraph 
Use /humanize on this paragraph with medium intensity: [paste text].
Keep a Light Edit 
Use /humanize --intensity light on this customer update. Keep all facts and numbers unchanged: [paste text].
Preserve Technical Detail 
Use /humanize --intensity medium on this technical explanation. Preserve terms, citations, and numbered steps: [paste text].
Review a Major Rewrite 
Use /humanize --intensity aggressive on this marketing draft. After rewriting, list any meaning changes to review: [paste text].

Best Practices

  • Review the output for meaning, factual accuracy, and tone before use.
  • Use light intensity when the draft already matches the intended voice.
  • Confirm policy approval before sending private text to an external service.

Avoid

  • Do not use the skill to misrepresent authorship or bypass institution policies.
  • Do not submit secrets, regulated data, or private customer information.
  • Do not use aggressive intensity when exact wording or legal meaning matters.

Frequently Asked Questions

Does this skill need an API key?
Yes. It uses HUMANIZERAI_API_KEY to authorize requests to HumanizerAI.
Does it send my text outside the tool?
Yes. The skill sends supplied text to the HumanizerAI API for processing.
Which intensity should I choose?
Use light for small edits, medium for balanced rewrites, and aggressive for larger rewrites.
Can it guarantee factual accuracy?
No. You must review facts, citations, numbers, and claims after rewriting.
Does it track credit usage?
The skill reports words processed and remaining credits when the API response provides them.
Is it suitable for sensitive content?
Only use it when external processing is allowed by your privacy and data-handling rules.

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/humanizerai/agent-skills/tree/main/skills/humanize

Ref

a06681402992ceae98ba04d54cfd4ab004862696

Maintenance freshness

7/18/2026

Usage

48 downloads · 269 views

File structure

📄 SKILL.md