slides-generator

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

• Third-party content exposure detected (low risk: 0.10). The workflow includes an optional research step that triggers web searches for statistics, comparisons, and trends, which can fetch outsider-authored text from arbitrary web pages.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill references an external tool via npx skills add vercel-labs/agent-browser, which constitutes a runtime external dependency from an unofficial GitHub repository source.