theme-detector

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly scrapes public FINVIZ pages (SKILL.md Step 2 and finviz_industry_scanner.py) and performs WebSearch-based narrative confirmation (SKILL.md Step 4 / methodology) and the agent is expected to read and act on that third-party content to set Confidence and Lifecycle scores, so untrusted web content can materially influence its decisions.