dailyhot-api

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

• Third-party content exposure detected (high risk: 0.80). The skill runs a local DailyHotApi (described in SKILL.md) that aggregates real-time hot lists from public, user-generated platforms (e.g., Weibo, Zhihu, B站, 抖音) and scripts/collect_trends.py fetches and parses those third‑party titles/URLs which are used to compute scores and drive downstream decisions, so untrusted external content can materially influence agent behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The ensure_running.sh script performs a runtime install and then executes the npm package "dailyhot-api" via "npm install dailyhot-api" (fetching code from the npm registry, e.g. https://registry.npmjs.org/dailyhot-api or https://www.npmjs.com/package/dailyhot-api), so remote code is fetched at runtime and executed as a required dependency.