daily-investment-report

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to read an API key placeholder (OPENAI_KEY = "sk-proj-...") or fetch it from a config file and then use it directly in command-line arguments (Authorization: Bearer $OPENAI_KEY via curl over SSH).

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

• Third-party content exposure detected (low risk: 0.10). The workflow uses web_search and scrapes external financial sites like TradingEconomics, Eastmoney, and Sina, allowing outsider-authored web content injection.