timesfm-forecasting

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

• Third-party content exposure detected (medium risk: 0.30). The required workflow processes user-supplied CSV files via forecast_csv.py, which parses and ingests free text data columns read by the agent.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill contains an operational inbound dependency on a pinned CDN-hosted Chart.js script via an HTML template generator (examples/global-temperature/generate_html.py:26), which is loaded at runtime by the generated HTML dashboard.