content-strategy

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

• Third-party content exposure detected (medium risk: 0.30). In the content-strategy skill’s required runtime workflow, the agent ingests user-provided free-text inputs such as “keyword exports,” “call transcripts,” “survey responses,” or “a list of 50 blog post ideas,” then analyzes and extracts content from that text to generate strategy outputs (e.g., “Keyword Data,” “Call Transcripts,” “Survey Responses,” and “Sales and Support Input”).