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
35 /100
Trust
High Risk

Enterprise Security

Undeclared shell execution via execSync

RCECredential TheftDoc MismatchPriv Escalation
Manual upload Apr 4, 2026
Open Report ↗
65 /100
Trust
Review

run402-test

Documentation mismatch - curl examples vs actual implementation

Doc MismatchSensitive AccessCredential Theft
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 ↗
35 /100
Trust
High Risk

maxianer

Undeclared external data transmission

Data ExfilDoc MismatchSensitive AccessCredential Theft
Manual upload Apr 4, 2026
Open Report ↗
45 /100
Trust
Review

ai-beauty

Contradictory claim of local-only processing

Doc MismatchData ExfilSupply ChainCredential Theft
Manual upload Apr 4, 2026
Open Report ↗
35 /100
Trust
High Risk

openclaw-memory-auto

Hardcoded Windows username path leaks user identity

Priv EscalationDoc MismatchCredential TheftSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

deepsafe-scan

Network access not declared in SKILL.md

Doc MismatchPriv EscalationCredential TheftSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
35 /100
Trust
High Risk

Bounty Hunter Agent

Hardcoded DeepSeek API Key in Documentation

Credential TheftDoc MismatchSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

kuaidi-query

Hardcoded API Credentials Exposed

Credential TheftPriv EscalationSupply ChainDoc Mismatch
Manual upload Apr 4, 2026
Open Report ↗
50 /100
Trust
Review

swarmrecall

Comprehensive agent context exfiltration to third-party

Data ExfilCredential TheftPriv EscalationSupply Chain
Manual upload Apr 4, 2026
Open Report ↗
55 /100
Trust
Review

xhs-skill-pusher

Shell execution not declared in SKILL.md

Doc MismatchSupply ChainSensitive AccessCredential Theft
Manual upload Apr 4, 2026
Open Report ↗
60 /100
Trust
Review

openclaw-usage-manager

API tokens stored in plaintext on disk

Credential TheftDoc MismatchPriv EscalationObfuscation
Manual upload Apr 4, 2026
Open Report ↗
55 /100
Trust
Review

oracle-report

Hardcoded QVeris API Key

Credential Theft
Manual upload Apr 4, 2026
Open Report ↗
55 /100
Trust
Review

clawclone

Missing implementation file

Doc MismatchCredential TheftSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
42 /100
Trust
Review

微信助手智能网关 (wechat-ai-bridge)

Undeclared external network communication

Doc MismatchData ExfilCredential TheftSupply Chain
Manual upload Apr 4, 2026
Open Report ↗
32 /100
Trust
High Risk

self-evolution-engine

Hardcoded Billing API Key in Source Code

Credential TheftData ExfilDoc MismatchSensitive Access
Manual upload Apr 4, 2026
Open Report ↗
← Previous
6 / 7
Next →