Skills/ClawHub/brain-core-skill

brain-core-skill@1.0.9

CAUTION· static only

Publisher claims: "Gunakan saat user minta reasoning/analisis mendalam atau ide kreatif lewat framework kognitif. Bukan mengganti identitas agent." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher pmuhammadagus-byte · publishing for 80 daysInstalls 657Last detonated 3d 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

LOW
Prompt injectionREADME.md:44 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file→ Pattern recognition dan analogical transferFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:151 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file→ Insight yang mengejutkan dan menyenangkanFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:485 · Prompt injection — known jailbreak technique reference…lity gate Node 18). Struktur skill sudah valid: description, PURPOSE, METADATA, dan trigger. Penambahan ini hanya memenuhi Node 18 secara eksplisit. Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:104 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file→ Apa yang akan mengejutkan dan menyenangkan mereka?Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:26 · Prompt injection — known jailbreak technique reference> **Tujuan**: Saat mengerjakan task yang butuh reasoning mendalam, gunakan framework berpikir terstruktur ini untuk meningkatkan kualitas analisis dan solusi.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:28 · Prompt injection — known jailbreak technique reference> **Mission**: Saat mengerjakan task, hasilkan output yang setara standar pakar kelas dunia: insightful, presisi, bernilai, dan intentional.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.md:179 · Prompt injection — known jailbreak technique reference · informational: not an instruction file · informational: not an instruction file- Open Source — bebas dimodifikasi dan didistribusikanFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈3,527 tok
1 file · 11 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