trading-analysis

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly runs local fetch scripts to retrieve external "news" and "macro" market data (see the Subagent 2 and Subagent 4 fetch commands: scripts/fetch_market_data.py --type news and --type macro), which the agents must read and incorporate into subsequent analyses and trading decisions, exposing the agent to untrusted third‑party headlines/content that could carry indirect prompt injection.