generate-presentation

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md (Step 1: Gather Content) explicitly instructs the agent to treat http(s) inputs as URLs and fetch them with the WebFetch tool to extract key content, meaning the agent will ingest arbitrary public web pages (untrusted, user-generated content) and use that content to draft slides and drive subsequent actions (image generation, slide creation, validation), enabling indirect prompt injection.