byted-ark-seedance-guide

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

• Third-party content exposure detected (high risk: 0.85). 该技能在运行时会对用户提供的 volcengine.com/docs/... URL 调用 fetch，将抓取到的官方文档正文（外部网页内容）作为可读文本进入 LLM 上下文；虽然来源是“官方文档”，但仍属于运行时获取的外部网页文本这一类 outsider 内容。

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

• Potentially malicious external URL detected (high risk: 0.80). The skill, at runtime, calls the external API endpoints (notably https://docs-api.cn-beijing.volces.com/api/v1/doc/fetch and /search) to retrieve document Content which is then injected into the agent's responses, so fetched remote content directly controls prompts and is a required dependency.