finance-explainer

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

• Third-party content exposure detected (low risk: 0.10). The workflow invokes search engines and web scraping scripts (scripts/research.py) via LLM runtime control to fetch public web pages and search queries.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script scripts/research.py makes HTTP POST requests to remote third-party API endpoints (Exa, Tavily, Serper, Firecrawl) during runtime execution, constituting common/reputable unofficial operational dependencies.