会话里有上传的 .pptx,且用户要把这份幻灯片填进一节已建的课(先 create_stage 建课,再 import_pptx 把页面追加进这节课堂,保留原版排版;课堂标题以 create_stage 为准,PPT 不接管)。随后逐页检查(有 render_scene_preview 就渲染看)并修 bad case,理解整课之后才写旁白/spotlight,最后 TTS。仅在用户要求时插入 quiz 或 interactive。不要重新规划整课。
64
81%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Low
Low-risk findings worth noting
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The workflow imports uploaded PowerPoint files (`.pptx`) via `import_pptx` and inspects/reads them page by page, exposing the agent to outsider-authored slide text.
636fab0
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.