moontv-openclaw-skill

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.85). Multiple indicators of risk: API/play domains use obscure numeric/.xyz hostnames and nonstandard TLDs, the GitHub repo is from an unestablished user, and an unknown LLM gateway (api.gptgod.online) is used — together these are common patterns for untrusted or malicious distribution even though no direct executable link is present.

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

• Third-party content exposure detected (high risk: 0.95). Outsider free text from public/third-party CMS sources is fetched at runtime via requests.get(f"{api_url}?ac=videolist..."), then its vod_content/synopsis is truncated and inserted into the LLM prompt in highlight_generator.build_prompt() and sent to client.chat.completions.create(...).