ux-interaction-taste

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

• Third-party content exposure detected (high risk: 0.70). The skill's Workflow explicitly accepts a "URL" and later instructs a "Browser check" to visit dev servers/take screenshots (SKILL.md, Workflow steps 1 and 3), which means the agent will fetch and interpret arbitrary web pages (untrusted third-party content) as part of its review and use that content to drive findings and next actions.