jiekou-multimodal

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). 不安全：该提示明确要求检查用户消息中是否包含以 sk_ 开头的 API Key 并在请求/命令中使用（包括“直接传参”示例和 Authorization 头的 curl 示例），这会使 LLM 需要读取并嵌入秘密值，存在泄露/外泄风险。

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

• Third-party content exposure detected (high risk: 0.90). The skill's required execution templates in SKILL.md and references/api-reference.md explicitly accept and process arbitrary external media URLs (e.g., "reference_images": ["图片URL"], "image_url"/"audio_url" in the API examples and the "附图片"/"附音频" examples), meaning the agent will fetch and analyze untrusted third‑party content that can materially change subsequent prompts and outputs.