kanchi-dividend-sop

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

• Third-party content exposure detected (high risk: 0.90). The skill's build_entry_signals.py (and SKILL.md prerequisites) explicitly fetch live data from FinancialModelingPrep (FMP_BASE_URL https://financialmodelingprep.com/api/v3) using an FMP_API_KEY, and that external data is parsed and used to compute entry signals and buy/ordering decisions, so third-party content can materially influence the agent's actions.