copywriting-tone-of-voice-creator

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow can spawn a research sub-agent that “Research current tone-of-voice norms… cite primary sources,” which implies fetching and ingesting public web content (outsider-authored pages/articles) into the agent’s LLM context via the research step.