hedgefundmonitor

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

• Third-party content exposure detected (high risk: 0.85). The skill calls OFR’s open REST API endpoints (e.g., /metadata/search, /metadata/query, /series/timeseries, /series/full, /categories) and ingests the returned JSON/CSV text into the agent context; since the content is fetched from a public third-party web service at runtime, it is outsider-authored free text (metadata descriptions/notes and CSV fields) that can include arbitrary strings.