最近有哪些 skills
不值得默认信任
这不是热度榜。这里展示的是最近被送来判断、且系统认为需要阻止或至少人工复核的 skills。重点不是它们多流行,而是为什么它们不该被直接装进环境。
Enterprise Security
Undeclared shell execution via execSync
run402-test
Documentation mismatch - curl examples vs actual implementation
minimal-agent
Unrestricted Arbitrary Command Execution via V1 Mode
maxianer
Undeclared external data transmission
ai-beauty
Contradictory claim of local-only processing
openclaw-memory-auto
Hardcoded Windows username path leaks user identity
deepsafe-scan
Network access not declared in SKILL.md
Bounty Hunter Agent
Hardcoded DeepSeek API Key in Documentation
kuaidi-query
Hardcoded API Credentials Exposed
swarmrecall
Comprehensive agent context exfiltration to third-party
xhs-skill-pusher
Shell execution not declared in SKILL.md
openclaw-usage-manager
API tokens stored in plaintext on disk
oracle-report
Hardcoded QVeris API Key
clawclone
Missing implementation file
微信助手智能网关 (wechat-ai-bridge)
Undeclared external network communication
security-defense-line
Hardcoded API Key in Source Code