add-flashcards

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 explicitly accepts arbitrary webpage URLs and instructs the agent to "Read/fetch the source material" and extract facts (see "Required Input" and "Steps"), so the agent will ingest untrusted third‑party web content and use it to drive generation/saving of flashcards, enabling indirect prompt injection.