ai-paid-ads

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). These links point to small/unknown domains and personal/open-source repositories (ai-skills.ai, skills.sh, and a GitHub user repo) rather than well-known vendor/CDNs; they don’t directly link to .exe/.msi files but are from relatively low‑trust sources and could be used to host or deliver malicious scripts/binaries, so treat them as moderately suspicious.

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

• Third-party content exposure detected (medium risk: 0.65). 该技能的运行时输入通过 materialText/materialFile/materialUrl 进入 contextComposer（references/form-schema.json），其中 materialUrl 对应“公开可访问的文章/页面/竞品内容”会被读取为可读文本并注入LLM上下文，属于外部网页内容来源的间接提示注入风险。