linkedin-post-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts and uses external website articles (see "Invocation Examples" — "/linkedin-post-generator Promote this article: [paste article or link]") and the Pillar Promotion / Workflow sections require the agent to "pull 2–3 key insights from the article" and map article content into eligible formats, which shows it will ingest and act on untrusted public web content as part of its mandatory workflow.