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。
mind-wander
Undeclared arbitrary Python code execution via sandbox_run()
stremio-cli
Explicit false statement about script status
Enterprise Security
Undeclared shell execution via execSync
minimal-agent
Unrestricted Arbitrary Command Execution via V1 Mode
lessac_offline_voice_system
False claim of offline operation
lock-me-in
Undeclared stealth/anti-detection browser scripts
calendar_memo
Undeclared shell command execution
claw-shell
Unrestricted shell execution with weak safety controls
aagent-system
Undeclared External Script Execution
buy-domain-helper
Undeclared shell execution via execSync and spawn
Rune
SSRF proof-of-concept with live metadata service IP
rewrite_question
Network capability declared as NONE but actual traffic exists
zanna-aperta
Undeclared arbitrary Docker command execution
skill-factory
Undeclared shell command execution via execSync
Grok Swarm
Undeclared credential access from OpenClaw auth profiles
clawguard-threat-detect
Hardcoded Reverse Shell Payloads in Documentation