trend-synthesis

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow reads and injects outsider-authored free text into the LLM context via per-theme evidence files produced by the upstream /trend-research (e.g., enriched-trends-{dimension}.json, claims-{dimension}.json, and their embedded claims[].citations/evidence text), which this skill then passes into the theme-case writers and composers as readable prompts/content.