scaffold-workshop

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

• Third-party content exposure detected (high risk: 0.80). The skill's Step 3 ("Research the feature") explicitly instructs the agent to use WebSearch and WebFetch to find and read AWS documentation and external blog posts (public web pages), which are open/public third‑party sources that the agent will read and use to decide SDK calls and workshop content.