frame-data-chart-nyt

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill explicitly requires embedding and rendering user-provided data (CSV/JSON or text conclusions) verbatim into the generated HTML/chart (titles, annotations, data labels), so if a user supplies secrets or API keys those values would be included in the LLM's output and thus risk exfiltration.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s required runtime workflow is to render user-provided content/data into an NYT-style chart frame (e.g., the example prompt instructs using “my content and data”), meaning outsider free text submitted by the provider user is ingested directly for chart/title/annotations generation.