hotel-core

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill requires the agent to extract and echo authorization links from CLI output and to insert returned tokens/reference numbers (e.g., authorization link, referenceNo) verbatim into subsequent CLI commands, forcing the LLM to handle and output potentially sensitive authorization values.

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.85). These URLs point to direct executable downloads from a third‑party GitHub repo (unknown/untested publisher) plus a custom short auth domain (rollinggo.store/s/xxx); direct .exe/.binary releases and opaque auth links are common malware distribution vectors and should be treated as suspicious unless the publisher and release are verified.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill's install script fetches and installs the rgg CLI at runtime from GitHub (calls https://api.github.com/repos/RollingGo-AI/oauth-hotel-cli-overseas/releases/latest and downloads from URLs like https://github.com/RollingGo-AI/oauth-hotel-cli-overseas/releases/latest/download/rgg-linux (or rgg-macos / rgg-win.exe)), which are required runtime downloads of an executable that will be run—so remote code is fetched and executed.