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.

349 Risky samples surfaced
4 New in 7 days
0 Platform misses surfaced
All Code Exec Credential Theft Data Exfil Priv Esc Supply Chain Doc Deception Prompt Injection Obfuscation
35 /100
Trust
High Risk

dianping-api

Remote Script Execution via curl|bash

Supply ChainObfuscationDoc Mismatch
Manual upload Apr 5, 2026
Open Report ↗
25 /100
Trust
High Risk

hive-commander

Covert credential extraction from runtime environment

Credential TheftData ExfilDoc MismatchPriv Escalation
Manual upload Apr 5, 2026
Open Report ↗
38 /100
Trust
High Risk

monid

Remote script execution via curl|bash from mutable branch

RCEPriv EscalationCredential TheftDoc Mismatch
Manual upload Apr 4, 2026
Open Report ↗
30 /100
Trust
High Risk

Unknown (E-SafeNet LOCK visible in binary)

Binary content in SKILL.md

ObfuscationDoc Mismatch
Manual upload Apr 4, 2026
Open Report ↗
33 /100
Trust
High Risk

mind-wander

Undeclared arbitrary Python code execution via sandbox_run()

RCEDoc MismatchPersistenceSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
25 /100
Trust
High Risk

minimal-agent

Unrestricted Arbitrary Command Execution via V1 Mode

RCEDoc MismatchPriv EscalationObfuscation
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

xiaohongshu-win

Hardcoded placeholder IP address

ObfuscationDoc MismatchSupply ChainSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

skill-factory

Undeclared shell command execution via execSync

RCEObfuscationSupply ChainDoc Mismatch
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

messenger_send_node

Undeclared Tor Network Routing

Data ExfilObfuscationSensitive AccessDoc Mismatch
Manual upload Apr 3, 2026
Open Report ↗