google-slides-skill

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

• Third-party content exposure detected (high risk: 0.90). This skill's code (slides_skill.py — e.g., cmd_comments and cmd_thumbnails and the "comments" command documented in SKILL.md) fetches and prints Google Drive/Slides presentation content and user comments and downloads slide thumbnails (user-provided images/URLs), which are untrusted, user-generated third-party content the agent reads and could act on (e.g., resolving comments), enabling indirect prompt injection.