crawl-xueqiu-my-timeline

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches user-generated posts from the public site xueqiu.com (see scripts/crawl_xueqiu_home_timeline_api.py which calls the /v4/statuses/home_timeline.json API) and SKILL.md/AGENTS.md require the agent to read the generated home_timeline_*.md and run subagents to analyze those posts and produce investment recommendations, so untrusted third-party content is ingested and can materially influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The script installs a required runtime tool via npm using the mirror URL "https://registry.npmmirror.com" (npm install -g agent-browser --registry=https://registry.npmmirror.com), which fetches and installs remote package code that will execute on the host, so this is a runtime external dependency that can execute remote code.