Skills/ClawHub/skill-architecture-standard

skill-architecture-standard@1.1.2

CAUTION· static only

Publisher claims: "Gunakan sebagai referensi saat user membuat, mereview, atau upgrade skill OpenClaw." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher pmuhammadagus-byte · publishing for 79 daysInstalls 644Last detonated 2d ago
What would fix thisWatchDispute verdict

Coverage

Static only; nothing was run yet.

The label rests on the code, the instruction files and the publisher. The honeypot run replaces this verdict when it completes.

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-11-08 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Prompt injection; Prompt injection. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

CRITICAL
Prompt injectionSKILL.md:44 · Prompt injection — known jailbreak technique reference| 4 | **Tahu bereaksi saat berubah** | Punya recovery, fallback, dan exit condition saat kondisi melenceng. |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:43 · Prompt injection — known jailbreak technique reference| 3 | **Tahu mengukur diri** | Mengeksekusi verification, evaluation, dan observability setelah bertindak. |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:14 · Prompt injection — known jailbreak technique reference…erjenjang, serta penambahan *Edge Cases*, *Anti-Patterns*, *Concrete Examples*, dan *Failure Modes* di setiap node relevan. --- ## 1. IDENTITY **Nama:** Skill A…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:46 · Prompt injection — known jailbreak technique reference**Tujuan akhir:** menaikkan seluruh skill ke taraf *agen nyata* — skill yang memutuskan, bertindak, memverifikasi, dan pulih — bukan dokumen pengetahuan yang hanya menunggu dibacakan.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:29 · Prompt injection — known jailbreak technique reference…bug, deploy, dsb) — ia menentukan **bagaimana** skill domain sebaiknya dibangun dan berperilaku. **Batas kewenangan:** Standard ini tidak mengganti logika domain …Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,325 tok
1 file · 2 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Unclaimed publisher≈ +8 on the totalClaim pmuhammadagus-byte: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
Publish a new version to ClawHub, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim pmuhammadagus-bytePropose a patch to the maintainer