market-top-detector

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

• Third-party content exposure detected (low risk: 0.10). The workflow requires web searches for market breadth and put/call ratios using query strings assembled from tool instructions, feeding outsider-accessible search snippet results into the scoring scripts.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill fetches breadth data at runtime from an external GitHub Pages CSV (https://tradermonty.github.io/market-breadth-analysis/market_breadth_data.csv), constituting a common/reputable unofficial operational dependency.