kuaishou-sentiment-dashboard

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly accepts a Kuaishou share link and, per SKILL.md and scripts/run.py, calls the backend parse-link (/api/comment-analysis/parse-link) and create-task endpoints to ingest and analyze public, user-generated Kuaishou comments (returned as labeledComments and aiInsights) which the agent reads and uses to produce operational advice, so untrusted third-party content can materially influence outputs.