中文 EN
Start Review
Risk Sample Stream

Which skills recently failed
or triggered trust review

This is not a popularity board. It shows recently reviewed skills that the system believes should be blocked or at least manually reviewed. The point is not how popular they are, but why they should not be installed blindly.

610 Risky samples surfaced
0 New in 7 days
0 Platform misses surfaced
All Malicious High Risk Suspicious
Sort by time Sort by risk
All Code Exec Credential Theft Data Exfil Priv Esc Supply Chain Doc Deception Prompt Injection Obfuscation
55 /100
Trust
Review

companion-skill

尝试覆盖 agent 安全拒绝机制

Prompt InjectionDoc Mismatch
ClawHub 16 days ago
Open Report ↗
45 /100
Trust
Review

award-contract-consistency-check-free

SKILL.md 声明不联网但实际存在外部网络请求

Doc MismatchData ExfilPriv EscalationPrompt Injection
ClawHub Sep 19, 2026
Open Report ↗
55 /100
Trust
Review

dlazy-idea2video

文档-行为严重不符

Doc MismatchPriv EscalationData ExfilPrompt Injection
ClawHub Jul 21, 2026
Open Report ↗
42 /100
Trust
Review

dating

主SKILL.md与子模块能力声明不一致

Doc MismatchSensitive AccessData ExfilSupply Chain
ClawHub Jun 24, 2026
Open Report ↗
55 /100
Trust
Review

sa-master

硬编码API密钥泄露

Credential TheftData ExfilPrompt InjectionSupply Chain
ClawHub Jun 14, 2026
Open Report ↗
52 /100
Trust
Review

browser-act

无法验证文档-行为一致性

Doc MismatchPriv EscalationSensitive AccessSupply Chain
ClawHub May 19, 2026
Open Report ↗
45 /100
Trust
Review

psychedelic-cognition

Safety mechanism bypass instruction

Prompt Injection
Manual upload Apr 4, 2026
Open Report ↗
55 /100
Trust
Review

feishu-evolver-wrapper

Dynamic code evaluation on untrusted input

ObfuscationPriv EscalationDoc MismatchPrompt Injection
Manual upload Apr 4, 2026
Open Report ↗