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.
High Risk
smyx-pet-grooming-stress-behavior-analysis
未声明的subprocess执行能力
ClawHub 12 days ago
Open Report ↗
High Risk
meta-analysis
Coze API 令牌以可逆混淆形式嵌入源代码，随技能公开发布
ClawHub 13 days ago
Open Report ↗
High Risk
smyx-family-conflict-aftercare-suggest-analysis
未声明的本地凭证数据库存储
ClawHub 16 days ago
Open Report ↗
High Risk
xhs-fav-export
wc3-code.mjs 严重混淆代码
ClawHub 19 days ago
Open Report ↗
High Risk
northcap-donor-badge
文档声称本地验证，实际发往外部 IP
ClawHub 20 days ago
Open Report ↗
High Risk
xhs-note-analyst
wc3-code.mjs 严重代码混淆
ClawHub 28 days ago
Open Report ↗
High Risk
klyc-pmm
curl|bash 管道执行远程脚本 — install-daemon
ClawHub Jul 28, 2026
Open Report ↗
High Risk
gpt-image-2
Hardcoded external IP with no DNS resolution
ClawHub Jun 22, 2026
Open Report ↗
High Risk
tunnel-proxy
Unrestricted PTY shell access granted to agent
ClawHub Jun 21, 2026
Open Report ↗
High Risk
tweet-monitor-pro
文档声称零依赖但实际存在外部脚本依赖
ClawHub Apr 19, 2026
Open Report ↗
High Risk
memolecard-auto
Cookie extraction and exfiltration to configurable external server
Manual upload Apr 5, 2026
Open Report ↗
High Risk
hive-commander
Covert credential extraction from runtime environment
Manual upload Apr 5, 2026
Open Report ↗
High Risk
gangtise-kb
Undeclared subprocess execution with missing binary
Manual upload Apr 5, 2026
Open Report ↗
High Risk
heycube-setup
Undeclared persistent hook installation
Manual upload Apr 5, 2026
Open Report ↗
High Risk
boss-ai-assistant
Hardcoded DashScope API Key
Manual upload Apr 4, 2026
Open Report ↗
High Risk
LLM Proxy
Critical content-blocking disabled — credential exfiltration not prevented
Manual upload Apr 4, 2026
Open Report ↗