a-stock-investment

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly queries a third-party search API (see scripts/search-stock.mjs calling https://api.tavily.com/search and the SKILL.md "数据来源" section) and prints/uses the returned AI-generated answer and result content as input to its analysis, so untrusted public web content can materially influence the agent's decisions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill calls the Tavily API at runtime (https://api.tavily.com/search) and directly prints the returned "answer" field into its output, so remote content from that URL can control the agent's responses.