content-marketer

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

• Third-party content exposure detected (high risk: 0.80). The skill's Capabilities and workflow explicitly call for ingesting public web data—e.g., "real-time SERP analysis and competitor content gap identification" in the Capabilities section and "Research competition" in the Response Approach—so the agent is expected to read and act on open/public third-party content that could contain untrusted instructions.