article-batch-illustration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly shows passing an API key as a command-line argument (--api-key "REMOVED_GEMINI_KEY") and lists an API Key value in the config, which requires the LLM or generated commands to include a secret value verbatim (high exfiltration risk).

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

• Third-party content exposure detected (medium risk: 0.30). 源自用户提供的文章内容在 Phase 1“读取文章/结构分析/生成提示词”中被直接提取并写入 Gemini 的图片 --prompt（随后由 scripts/generate_image.py 以 contents.parts[0].text 发送到 https://generativelanguage.googleapis.com），因此存在被外部投喂的自由文本影响提示词的间接注入暴露。