Skills ki-register-use-case-documenter
📦

ki-register-use-case-documenter

Content revision r1 Safe ⚙️ External commands🌐 Network access📁 Filesystem access🔑 Env variables

Document KI-Register AI Use Cases

AI governance records are hard to create from code, interviews, and operational context. This skill guides capture, validation, review, and confirmed KI-Register submission.

Supports: Claude Codex Code(CC)
🥉 78 Bronze

Install with my Agent

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

Agent request
Review the Skillstore skill "ki-register-use-case-documenter" from https://skillstore.io/skills/egonso-ki-register-use-case-documenter.md and its manifest at https://skillstore.io/api/skills/egonso-ki-register-use-case-documenter/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.

Markdown detail GET /skills/egonso-ki-register-use-case-documenter.md Signed manifest GET /api/skills/egonso-ki-register-use-case-documenter/manifest Signed lockfile GET /api/skills/egonso-ki-register-use-case-documenter/lockfile

Test it

Using "ki-register-use-case-documenter". A compliance lead asks for a record of a customer support AI workflow.

Expected outcome:

The skill produces a plain-language use case summary, required governance fields, missing evidence, and a validated manifest path.

Using "ki-register-use-case-documenter". An engineering team points the skill at a repository with AI routes and prompt files.

Expected outcome:

The skill identifies candidate systems, records evidence-backed data categories, lists unknowns, and prepares files for human review.

Using "ki-register-use-case-documenter". A registered team wants to submit a confirmed manifest.

Expected outcome:

The skill validates locally, asks for explicit approval, then submits only when credentials and register details are available.

Security Audit

Safe
v6 • 7/9/2026 Open versioned report

Most static command detections are Markdown paths or documentation references, but several instructions direct the agent to run local Node CLI commands. The skill also submits governance manifests to a KI-Register API endpoint after explicit human confirmation. No prompt injection or covert credential exfiltration was found.

2
Files scanned
120
Lines analyzed
8
Review items
0
False positives ignored
Capability review items (8)

These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.

Medium
SKILL.md:29
Ruby/shell backtick execution
1. If the Agent Kit repository is present, use its CLI from the package root: `node ./bin/studio-age
This line instructs the agent to invoke a local Node CLI. Running project-local scripts can execute untrusted code if the repository or CLI is not trusted.
Medium
SKILL.md:30
Ruby/shell backtick execution
2. If the Agent Kit is vendored inside another repo as `agent-kit/`, use: `node ./agent-kit/bin/stud
This line instructs the agent to run a vendored Node CLI from the target repository. That is legitimate for the workflow but still external command execution.
Medium
SKILL.md:31
Ruby/shell backtick execution
3. If no local onboarding exists, run `studio-agent onboard` or `node ./bin/studio-agent.mjs onboard
This line gives onboarding commands that an agent may execute. The commands are expected, but they still run local or installed tooling.
Medium
SKILL.md:41
Ruby/shell backtick execution
- **Low-friction capture**: When enough context is already known, run `studio-agent capture` with fl
This line instructs the agent to run studio-agent capture with flags or input JSON. That is external command execution and should require trust in the CLI and inputs.
Medium
SKILL.md:68-73
Ruby/shell backtick execution
```bash
The fenced block contains Node CLI commands for onboarding, capture, interview, and validation. These are intended operations but still execute local code.
Medium
SKILL.md:77-84
Ruby/shell backtick execution
```bash
The fenced block exports variables and runs the Node CLI submit command against a manifest. This is command execution with credential and submission context.
Low
SKILL.md:32
Hardcoded URL
4. If the user does not have a KI-Register account or API key, send them to `https://kiregister.com/
The line directs users to KI-Register account and settings pages, which is intentional onboarding network use. It is not covert, but it depends on an external service.
Low
SKILL.md:83
Hardcoded URL
--endpoint "https://kiregister.com/api/agent-kit/submit"
The submit command uses a hardcoded KI-Register API endpoint, sending the manifest to an external service after confirmation. This is intended behavior but still a real external network destination.

Risk Factors

⚙️ External commands (18)
SKILL.md:22 SKILL.md:23 SKILL.md:29 SKILL.md:30 SKILL.md:31 SKILL.md:32 SKILL.md:33 SKILL.md:41 SKILL.md:47 SKILL.md:68-73 SKILL.md:73-77 SKILL.md:77-84 SKILL.md:84-101 SKILL.md:101-102 SKILL.md:102-103 SKILL.md:103-108 SKILL.md:108-109 SKILL.md:109
🌐 Network access (4)
SKILL.md:5 SKILL.md:7 SKILL.md:32 SKILL.md:83
📁 Filesystem access (1)
SKILL.md:109
🔑 Env variables (3)
SKILL.md:11 SKILL.md:33 SKILL.md:78
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/egonso-ki-register-use-case-documenter/audits/6?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/egonso-ki-register-use-case-documenter/security.svg)](https://skillstore.io/skills/egonso-ki-register-use-case-documenter?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/egonso-ki-register-use-case-documenter?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/egonso-ki-register-use-case-documenter/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/egonso-ki-register-use-case-documenter.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

Egonso. (2026). ki-register-use-case-documenter security audit report (audit version 6) [Author version unspecified]. Skillstore. https://skillstore.io/skills/egonso-ki-register-use-case-documenter/audits/6

BibTeX citation

@techreport{egonso-egonso-ki-register-use-case-documenter-2026, author = {Egonso}, title = {ki-register-use-case-documenter security audit report (audit version 6)}, institution = {Skillstore}, year = {2026}, number = {6}, url = {https://skillstore.io/skills/egonso-ki-register-use-case-documenter/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: "ki-register-use-case-documenter security audit report (audit version 6)" version: "unspecified" type: report authors: - name: "Egonso" date-released: "2026-07-09" url: "https://skillstore.io/skills/egonso-ki-register-use-case-documenter/audits/6" identifiers: - type: other value: "skillstore:egonso-ki-register-use-case-documenter:audit:6" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: Medium
55
Architecture
85
Maintainability
87
Content
67
Community
91
Spec Compliance

What You Can Build

Prepare Governance Records

Document an AI workflow with purpose, owner, data categories, controls, risks, and review artifacts.

Map AI Features From Code

Inspect a repository and turn visible routes, prompts, scripts, and docs into a reviewable use case draft.

Collect Supplier Evidence

Interview stakeholders and capture the facts needed for procurement, vendor review, and internal AI governance.

Try These Prompts

Create a Basic Interview Draft 
Use this skill to interview me about an AI workflow and create a KI-Register use case draft. Ask one question at a time.
Inspect a Repository 
Use this skill to inspect this project and document any AI application or workflow with evidence-backed facts and unknowns.
Validate an Existing Manifest 
Use this skill to review my existing KI-Register use case files, validate the manifest, and list missing governance fields.
Prepare Confirmed Submission 
Use this skill to prepare a validated manifest for KI-Register submission. Show the summary, destination, and blockers before asking for confirmation.

Best Practices

  • Review generated summaries with the owner before validation or submission.
  • Keep KI-Register API keys in environment variables or a secret store.
  • Mark uncertain AI Act details as unknown for specialist review.

Avoid

  • Do not submit inferred records without explicit human approval.
  • Do not store API keys in manifests, README files, logs, or screenshots.
  • Do not overstate risk class when source evidence is incomplete.

Frequently Asked Questions

Does this skill decide EU AI Act risk class?
No. It documents facts for governance review and leaves uncertain classification decisions for qualified reviewers.
Can it work from a codebase only?
Yes. It can inspect local files and mark unsupported details as unknown for follow-up.
Can it interview business users?
Yes. It can ask targeted questions about purpose, data, controls, human review, and artifacts.
Will it submit data automatically?
No. The skill requires a visible summary and explicit human confirmation before submission.
What credentials are needed for submission?
Submission needs a KI-Register API key and register identifier available through approved local configuration.
What files does it produce?
It produces a machine-readable manifest and a human-readable README for review workflows.

Developer Details

Author

Egonso

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/Egonso/ki-register-agent-kit/tree/main/skills/ki-register-use-case-documenter/

Ref

26421118b848d9f1efc0aa169d8a7a9e7e0a877e

Maintenance freshness

7/18/2026

Usage

1 downloads · 0 views

File structure

📁 agents/

📄 openai.yaml

📄 SKILL.md