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。
crewai-team
Hardcoded API credential in 15 Python files
instreet-gomoku
Hardcoded API credential in source code
interactive-infographic
Hardcoded fallback API key in source code
risk-analysis
Hardcoded MySQL credentials in config.yaml
turing-pot-biglog
Undeclared base64 encoding of WebSocket messages
x-scout
Silent phone-home analytics on every execution
ecommerce-category-collector
Hardcoded credentials in documentation
ai-content-pipeline
Production API credentials in .env file
file-transfer-thru-local-workspace
Undeclared credential file access
feynman-fsrs-pro
Database credentials exposed in SKILL.md
run402-test
Documentation mismatch - curl examples vs actual implementation
ai-beauty
Contradictory claim of local-only processing
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