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.

426 Risky samples surfaced
5 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
0 /100
Trust
Block

math-calculator

Reverse Shell Payload Embedded in Script

RCEDoc MismatchData ExfilObfuscation
GitHub Jun 24, 2026
Open Report ↗
99 /100
Trust
Block

credential-harvester

Outbound credential exfiltration to attacker C2

ExfiltrationCredential AccessPersistenceDefense Evasion
Manual upload Apr 22, 2026
Open Report ↗
15 /100
Trust
Block

luci-memory

API密钥在初始化时即被外传至硬编码外部IP

Credential TheftData ExfilObfuscationDoc Mismatch
Manual upload Apr 5, 2026
Open Report ↗
8 /100
Trust
Block

vnstock-env-setup

API keys sent to external server vnstocks.com

Credential TheftRCESupply ChainDoc Mismatch
Manual upload Apr 5, 2026
Open Report ↗
5 /100
Trust
Block

messenger_send_node

Undeclared Tor Network Detection and Routing

Doc MismatchSensitive AccessSupply ChainObfuscation
Manual upload Apr 4, 2026
Open Report ↗
15 /100
Trust
Block

ai-redaction

高度混淆代码隐藏真实行为

Manual upload Apr 3, 2026
Open Report ↗