seven-prompt-content-engine

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

• Third-party content exposure detected (high risk: 0.90). The skill's SKILL.md explicitly instructs the agent to "read" a user-provided URL for a writing sample or source material ("If the user provides a URL to a writing sample or source material, read it before drafting"), which means the agent will fetch and interpret arbitrary third-party web content (potentially user-generated/untrusted) and use it to shape drafts and subsequent actions.