ai-short-drama

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). Most links are GitHub, documentation, and badge/CDN URLs (low-risk), but the package includes personal/low‑profile GitHub repos and an installer instruction that pipes a remote script to bash (https://jimeng.jianying.com/cli | bash), which is a common malware vector if run without vetting — exercise caution and review the repos/scripts before executing.

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

• Third-party content exposure detected (high risk: 0.75). 在 Phase 0 的“市场情报扫描”步骤中，skill 会进行 WebFetch/网页抓取（如 woshipm/36氪/腾讯新闻等）并把抓取到的爆款拆解文章正文作为文本写入 01_市场情报.md，随后该内容会进入后续 LLM 生成流程（间接提示注入风险）。

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

• Potentially malicious external URL detected (high risk: 0.90). The skill includes a runtime install command that fetches and executes remote code — "curl -fsSL https://jimeng.jianying.com/cli | bash" — to install the dreamina CLI, which the skill requires to run text2image/image2video commands, so this URL is a runtime external dependency that executes remote code.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)