trend-spotter

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 is described as monitoring “social conversations,” “emerging topics,” “viral content,” “hashtags,” and “cultural moments,” which in practice requires ingesting outsider-authored free-form text from third-party platforms (e.g., posts/comments) into the agent’s LLM context for trend analysis.