Skills/ClawHub/vn-guide

vn-guide@1.0.0

CAUTION· static only

Publisher claims: "Hướng dẫn toàn diện — giải thích how/why, sửa lỗi người dùng, tối ưu pipeline viết gốc & dịch thuật với bộ kỹ năng kb-vn. Version dành cho người đã biết basics." Observed in sandbox: static analysis only — behavior not yet observed.

Registry ClawHubPublisher kaibazax-dev · publishing for 157 daysInstalls 495Last detonated 32 h 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 2026-11-13 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:17 · Prompt injection — known jailbreak technique reference**Hệ quả:** Đừng jailbreak. Dùng skill chuyên biệt cho từng task -> giảm nhiễu attention -> AI khôn hơn.Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:15 · Prompt injection — known jailbreak technique reference… bị bỏ qua vì AI đang ở chế độ "làm việc". Đây là lý do skill hoạt động tốt hơn jailbreak — jailbreak tạo nhiễu attention, skill tạo khuôn khổ chuyên biệt. **Hệ quả:*…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:275 · Prompt injection — known jailbreak technique reference| Tại sao không nên jailbreak? | Tạo nhiễu attention → AI ngu đi. Dùng skill chuyên biệt. |Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionSKILL.md:288 · Prompt injection — known jailbreak technique reference2. **Tránh jailbreak** → giảm nhiễu attention vô ích → AI khôn hơnFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01

Cost to the agent

Instructions loaded
≈3,231 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 kaibazax-dev: 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 kaibazax-devPropose a patch to the maintainer