social-sbti

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

• Third-party content exposure detected (high risk: 1.00). The skill's required workflow fetches public, user-generated social media posts (see Step 2 "抓取动态" and the fetch_x.py / fetch_jike.py scripts) and Claude is instructed to read ~150 sampled posts (Step 3 and SCORING_RUBRIC.md) to produce scores and drive subsequent matching/rendering, so untrusted third‑party content is ingested and can materially influence the agent's decisions and outputs.