data-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to print data rows and embed raw data as a JS variable in the generated HTML, which forces the LLM to include user-provided values verbatim (risking exfiltration of any secrets present in the uploaded files).

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

• Potentially malicious external URL detected (high risk: 0.90). The report template includes a runtime script tag that loads and executes Chart.js from https://cdn.jsdelivr.net/npm/chart.js@4, which is remote code the skill relies on to render charts in the generated HTML.