humanize-text

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

• Third-party content exposure detected (low risk: 0.10). The skill accepts user-provided text, screenshots, and Figma URLs (via a Figma MCP server) for analysis, which involves ingesting web content or user-selected URLs rather than unrequested monitored feeds.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill executes runtime installation instructions via npx skills add fetching a third-party GitHub repository (gregorymm/humanize-text), representing a common unofficial operational dependency.