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。
feishu-evolver-wrapper
Dynamic code evaluation on untrusted input
buy-domain-helper
Undeclared shell execution via execSync and spawn
security-defense-line
Hardcoded API Key in Source Code
melo-tts-metadata-creator
Undeclared silent package installation
chattts
Hardcoded fallback IP address
wip-xai-grok
Undeclared shell:WRITE via 1Password CLI execSync
Rune
SSRF proof-of-concept with live metadata service IP
sql_audit
Hardcoded JWT token in source code
hostlink
No allowed-tools declaration despite full shell access
1panel
Undeclared arbitrary command execution via 1Panel Terminal API
Bitget Trader
Exposed API Credentials in Plaintext
Grok Swarm
Undeclared credential access from OpenClaw auth profiles
agentcop
Undeclared network communication to agentcop.live
safe-flow-solana-skill
Undocumented shell command execution
figma-agent
Undeclared scanning of Claude Code credential store
flyai-transit-tour
Undeclared shell execution in workflow