kol-pricing

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow calls UnifAPI to fetch public X/Twitter profile/tweet text (outsider-authored content) via x/users/by/username/{username} and x/users/{id}/tweets, which becomes readable prose in the agent’s LLM context for tiering/ROI and evidence summarization.