Skills personwise-create-course

📦

personwise-create-course

Name: personwise-create-course
Author: personwiseai

Content revision r1 High Risk 🌐 Network access⚙️ External commands📁 Filesystem access

Create Polished PersonWise Courses

Building a complete course from mixed materials requires careful structure, review, and state tracking. This skill guides PersonWise creation through reliable checkpoints and verified completion.

Supports: Claude Codex Code(CC)

⚠️ 38 Poor

Stop for confirmation before installing.

Review the plan and obtain explicit user consent before changing files.

Install with my Agent

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

Agent request

Review the Skillstore skill "personwise-create-course" from https://skillstore.io/skills/personwiseai-personwise-create-course.md and its manifest at https://skillstore.io/api/skills/personwiseai-personwise-create-course/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/personwiseai-personwise-create-course.md Signed manifest GET /api/skills/personwiseai-personwise-create-course/manifest Signed lockfile GET /api/skills/personwiseai-personwise-create-course/lockfile

Test it

Using "personwise-create-course". Create a private eight-slide onboarding course from the employee handbook.

Expected outcome:

Created the course from the named handbook, reviewed the outline and narration, verified all images, and confirmed private playability. The completion record includes source status, revisions, and project identifiers.

Using "personwise-create-course". Resume my product safety course and share it with anyone who has the link.

Expected outcome:

Resumed the existing run from current state, completed the remaining review checkpoint, enabled link access, and returned the verified share URL.

Using "personwise-create-course". Review the visuals in my unpublished history course.

Expected outcome:

Downloaded ordered review sheets for every slide.
Recorded factual, text, layout, and continuity findings.
Regenerated only the failed slides and rechecked the changed images.

Security Audit

High Risk

v1 • 8/5/2026 Open versioned report

The 127 static alerts are false positives caused by documented commands, Markdown formatting, bounded installer checks, and signed descriptor data. Two semantic risks remain: the skill installs externally hosted binaries without enforced native signatures and executes update commands supplied through remote responses. No prompt injection attempt was found.

Files scanned

1,496

Lines analyzed

Review items

False positives ignored

Confirmed security concerns (2)

High

assets/bootstrap.sh:132-180 assets/bootstrap.ps1:10-92

Externally Hosted Executable Lacks Native Signature Enforcement

The bootstraps download and install an opaque PersonWise executable. Pinned hashes protect integrity, but native signature enforcement is disabled for the reviewed Windows and macOS release.

Both installers explicitly fetch and deploy an executable, and the native signature gates are disabled or conditional. Checksums reduce tampering risk but do not make the binary auditable.

High

SKILL.md:39-45 references/connection-and-auth.md:33-47

Remote Update Action Is Executed as a Command

The workflow tells the agent to run the exact action command returned by update responses. It does not require structural parsing or an explicit command allowlist.

The instructions directly require execution of response-provided command text after approval. A compromised service or CLI response could convert this update channel into command execution.

Risk Factors

🌐 Network access (2)

assets/bootstrap.ps1:43 assets/bootstrap.sh:132

⚙️ External commands (50)

📁 Filesystem access (7)

assets/bootstrap.sh:81 assets/bootstrap.sh:83 assets/bootstrap.sh:128 assets/bootstrap.sh:16 assets/bootstrap.sh:18 assets/bootstrap.sh:128 assets/bootstrap.sh:180

Audited by: codex

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

Copy report link

https://skillstore.io/skills/personwiseai-personwise-create-course/audits/1?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/personwiseai-personwise-create-course/security.svg)](https://skillstore.io/skills/personwiseai-personwise-create-course?utm_source=security_passport_badge)

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/personwiseai-personwise-create-course.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

personwiseai. (2026). personwise-create-course security audit report (audit version 1) [Author version unspecified]. Skillstore. https://skillstore.io/skills/personwiseai-personwise-create-course/audits/1

BibTeX citation

@techreport{personwiseai-personwiseai-personwise-create-course-2026,
  author = {personwiseai},
  title = {personwise-create-course security audit report (audit version 1)},
  institution = {Skillstore},
  year = {2026},
  number = {1},
  url = {https://skillstore.io/skills/personwiseai-personwise-create-course/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: "personwise-create-course security audit report (audit version 1)"
version: "unspecified"
type: report
authors:
  - name: "personwiseai"
date-released: "2026-08-05"
url: "https://skillstore.io/skills/personwiseai-personwise-create-course/audits/1"
identifiers:
  - type: other
    value: "skillstore:personwiseai-personwise-create-course:audit:1"
    description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium

Architecture

Maintainability

Content

Community

Spec Compliance

What You Can Build

Convert Training Documents

Turn approved internal documents into a source-grounded course with structured slides, narration, and private access.

Develop Expert Lessons

Create a focused course from a topic, then review teaching progression, factual support, and visual quality.

Maintain Published Courses

Resume, refine, repair, query, publish, or share an existing PersonWise course from current service state.

Try These Prompts

Create a Topic Course

Create a private PersonWise course about [topic] for [learner group]. The outcome is [outcome]. Use [number] slides and a [tone] teaching style.

Build From Documents

Create a materials-only PersonWise course from [file paths]. Preserve the source facts, target [learner group], and make the final course private.

Review and Refine

Open PersonWise course [project ID]. Review the outline, narration, page text, and images. Apply only objective corrections and preserve slide order.

Resume and Distribute

Resume PersonWise run [run ID] with account [alias]. Reconcile current state, complete pending reviews, enable [private or link] access, and verify playability.

Best Practices

State the learner, outcome, source boundary, page count, and access target before creation.
Use only named files and request approval before using agent-discovered local content.
Read fresh run and course state before every mutation and after every interruption.

Avoid

Do not interpolate course content into shell commands or expose credentials and signed URLs.
Do not claim completion, publication, or visual quality from queued or partial state.
Do not purchase credits, broaden visibility, or create additional courses without authorization.