Skills broken-skill
📦

broken-skill

Content revision r1 Safe

Audit Broken Skill Fixtures

Skill authors need examples that expose incomplete marketplace metadata. This fixture provides a minimal broken skill for testing package validation and adapter handling.

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 "broken-skill" from https://skillstore.io/skills/yaojingang-broken-skill.md and its manifest at https://skillstore.io/api/skills/yaojingang-broken-skill/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/yaojingang-broken-skill.md Signed manifest GET /api/skills/yaojingang-broken-skill/manifest Signed lockfile GET /api/skills/yaojingang-broken-skill/lockfile

Test it

Using "broken-skill". Explain why this fixture fails packaging validation.

Expected outcome:

The skill defines basic metadata but does not provide usable default prompt content. A packager should reject it or mark it as incomplete.

Using "broken-skill". Summarize the security posture of this fixture.

Expected outcome:

The fixture is metadata-only and contains no scripts, network behavior, file operations, or secret access. The primary issue is completeness, not security.

Using "broken-skill". Describe a useful test based on this skill.

Expected outcome:

A validation test can confirm that adapter tooling reports missing prompt behavior while still reading display metadata correctly.

Security Audit

Safe
v4 • 7/8/2026 Open versioned report

No static findings were reported, and no semantic security issues were found in SKILL.md or agents/interface.yaml. The files contain metadata for an incomplete packaging fixture, with no executable code, network calls, filesystem access, or secret access.

2
Files scanned
27
Lines analyzed
0
Review items
0
False positives ignored
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
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/yaojingang-broken-skill/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

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

HTML badge

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

Embed card

<iframe src="https://skillstore.io/embed/skills/yaojingang-broken-skill.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

yaojingang. (2026). broken-skill security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/yaojingang-broken-skill/audits/4

BibTeX citation

@techreport{yaojingang-yaojingang-broken-skill-2026, author = {yaojingang}, title = {broken-skill security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/yaojingang-broken-skill/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: "broken-skill security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "yaojingang" date-released: "2026-07-08" url: "https://skillstore.io/skills/yaojingang-broken-skill/audits/4" identifiers: - type: other value: "skillstore:yaojingang-broken-skill:audit:4" 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

Validate Packaging Errors

Confirm that a packager reports missing prompt metadata instead of accepting incomplete skill definitions.

Review Marketplace Metadata

Use the fixture as a small reference when checking required skill fields and adapter metadata.

Test Adapter Degradation

Exercise metadata-only adapter behavior when a skill cannot provide a full prompt interface.

Try These Prompts

Inspect This Fixture 
Review this skill fixture and summarize why it is considered broken. Focus on missing user-facing prompt content and packaging impact.
Compare With a Valid Skill 
Compare this fixture with a valid skill definition. List the required fields that are present and the prompt behavior that is missing.
Create a Packaging Test 
Design a packaging validation test that uses this fixture. Describe the expected failure and the message a developer should see.
Define Adapter Rules 
Propose adapter validation rules for metadata-only skills. Include how Claude, Codex, and Claude Code should handle incomplete prompts.

Best Practices

  • Use this fixture only in validation or packaging test suites.
  • Pair it with a valid fixture to verify both success and failure paths.
  • Keep failure expectations explicit so test results remain easy to diagnose.

Avoid

  • Do not publish this fixture as a user-facing productivity skill.
  • Do not treat metadata-only adapter output as a complete skill experience.
  • Do not add executable behavior just to hide a missing prompt interface.

Frequently Asked Questions

What is this skill for?
It is a test fixture for packaging and adapter validation, especially missing prompt interface behavior.
Can end users run useful tasks with it?
No. It does not include a usable default prompt or workflow instructions.
Does it execute commands?
No executable code or command script was found in the scanned files.
Why mention Claude, Codex, and Claude Code?
Marketplace users may validate how different AI tools handle incomplete skill metadata.
Is the issue a security problem?
No evidence of a security issue was found. The main issue is incomplete skill functionality.
How should authors fix a similar skill?
Add clear prompt instructions and complete required interface fields before packaging or publication.

Developer Details

Author

yaojingang

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/yaojingang/yao-meta-skill/tree/main/tests/fixtures/package_missing_interface_field

Ref

64ca8af0f54a325752f08bd54e52151061ea659a

Maintenance freshness

7/21/2026

Usage

2 downloads · 0 views

File structure

📁 agents/

📄 interface.yaml

📄 SKILL.md