slidespeak-generator

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

• Third-party content exposure detected (high risk: 0.80). The skill's main workflow (SKILL.md, "Usage Approach" step 3: "Gather supporting information
• Use web_search when needed for facts, data, examples") explicitly instructs the agent to fetch public web content, and the API schema (resources/api_schema.json imageRequest with type "url") plus scripts/config_builder (which enables fetch_images=True) show the agent can ingest arbitrary external URLs/images — untrusted third‑party content that the agent will read and use to shape slide content and decisions.