hotel-price-monitor

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.80). These are direct downloads of platform executables from a GitHub releases page belonging to an unverified/unknown repository (RollingGo-AI) and an install script that fetches/runs those binaries — a common and risky distribution pattern for malware unless the repo and builds are independently verified.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow uses the rgg CLI for hotel search/detail/price queries, and those commands necessarily fetch and return hotel descriptions/cancellation policy text from external hotel/booking sources; that returned free-form prose is then placed into the agent’s LLM context (indirect prompt-injection risk from public web/third-party content).

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 and fallback logic download and install a remote CLI binary that the skill requires and will execute at runtime (e.g., https://github.com/RollingGo-AI/oauth-hotel-cli-overseas/releases/latest/download/rgg-linux), so external content fetched from these GitHub release URLs directly supplies executable code used by the agent.