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's scripts (scripts/crawl_xueqiu_home_timeline_api.py) fetch public, user-generated timeline data from xueqiu.com and the SKILL.md and subagent instruction templates explicitly tell the AI to read/analyze the generated home_timeline_*.md (third‑party posts), which can materially influence TODO creation, subagent dispatch and generated reports—so untrusted content can indirectly inject instructions.

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

• Potentially malicious external URL detected (high risk: 0.90). The crawl script invokes agent-browser at runtime to fetch live data from https://xueqiu.com/v4/statuses/home_timeline.json and that fetched JSON/Markdown is injected into the AI analysis pipeline (model context) and is required for the skill to operate, so it is a runtime external dependency that controls the agent's inputs.