ai-pptx

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

• Third-party content exposure detected (medium risk: 0.65). 该技能在运行时会把用户提供的 materialUrl 指向的“公开演示链接”内容（网页/文档正文）解析为可读幻灯片文本并进入 LLM 上下文；该文本属于外部网页/第三方作者的自由文本，存在间接提示注入风险。

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

• Potentially malicious external URL detected (high risk: 0.90). The runner script (scripts/run.py) performs runtime POSTs to the skill execution endpoint (default https://ai-skills.ai/api/execute via AISKILLS_BASE_URL), which executes the skill remotely and thus relies on external code/behavior to control prompts and produce results.