skill-publish-sync

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The document shows commands that embed API tokens directly in CLI flags (e.g., "skillhub login --key skh_xxx" and "--token skh_xxx"), which would require the agent/LLM to include user secrets verbatim in generated commands — an exfiltration risk.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). The SKILL.md instructs curl|bash from a third‑party Tencent COS URL (skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/install.sh), which is a direct remote install script and a high-risk distribution vector for malware.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill documentation includes a runtime "curl ... | bash" installer that fetches and executes remote code from https://skillhub-1388575217.cos.ap-guangzhou.myqcloud.com/install/install.sh (used to install the required skillhub CLI), which is a high-confidence remote-execute dependency.