diffusers-ascend-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (SKILL.md "API 文档索引与按版本检索" and references/api-navigation.md) explicitly instructs the agent to enumerate and fetch Diffusers documentation from public third‑party sources (GitHub, huggingface.co, and hf-mirror.com — e.g., using the gh api command), so the agent will read and act on untrusted external web content that can influence its subsequent tool use and recommendations.