andrew-ng

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

• Third-party content exposure detected (high risk: 0.90). The skill's Agentic Workflow Iteration explicitly instructs the agent to "perform web research to fetch context" (SKILL.md and references/frameworks.md), which requires fetching and reading open/public web content that the agent will interpret and use to drive drafts and subsequent actions, exposing it to untrusted third‑party content and potential indirect prompt injection.