powerpoint-automation

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests open web content (e.g., blog/articles such as Zenn/Qiita) as part of its required EXTRACT workflow—see SKILL.md quick start and the Purpose: Blog to Presentation (references/instructions/purpose-blog.instructions.md) which instructs fetching article HTML and downloading images via scripts like extract_images.py—so untrusted, user-generated third‑party content is parsed and used to drive downstream decisions (content.json, summarization, translation, build), enabling indirect prompt injection.