Skills/ClawHub/aurum-brain

aurum-brain@2.0.1

CAUTION· static only

Publisher claims: "Gunakan saat user meminta reasoning mendalam bertahap, self-correction, atau output anti-repetitif terverifikasi pada tugas nyata." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher pmuhammadagus-byte · publishing for 83 daysInstalls 714Last detonated 6d 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:16 · Prompt injection — known jailbreak technique reference…yang dipasang di atas seluruh skill OpenClaw untuk menjaga kualitas, keandalan, dan perilaku agentik setiap respons. Ia bukan skill pelaksana tertentu; ia adalah *…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:3 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file> Gunakan saat mengaktifkan lapisan OS agent adaptif: pikiran terbuka terhadap skill, perilaku berbasis data, penalaran bertahap, koreksi-diri, anti-pengulangan, dan eksekusi tugas yang agentik.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:7 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file…n terbuka terhadap skill, berbasis data, bernalar bertahap, berkoreksi sendiri, dan menghindari pengulangan. Ia diaktifkan untuk meningkatkan kualitas dan keandala…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:45 · Prompt injection — known jailbreak technique reference**Outcome yang diharapkan:** jawaban yang jelas, terstruktur, terverifikasi, tidak repetitif, dan jujur terhadap batasan.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:21 · Prompt injection — known jailbreak technique reference…tersedia, menerima skill baru, bekerja secara terstruktur, memverifikasi hasil, dan terus meningkatkan kualitas respons berdasarkan koreksi yang valid." **Batasan…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 referenceGunakan untuk meningkatkan kualitas dan keandalan setiap respons agent melalui:Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈5,207 tok
1 file · 6 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