market-top-detector

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests public third‑party data that the agent must read and act on — e.g., Phase 1 in SKILL.md / README requires WebSearch for S&P 50DMA breadth and the CBOE put/call ratio (public sites like barchart.com and cboe.com), scripts/breadth_csv_client.py auto‑fetches TraderMonty’s public GitHub Pages CSV, and fmp_client.py pulls live quotes from the FinancialModelingPrep API — those untrusted external inputs are parsed and directly influence scoring and recommended actions.