design

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs using the pre-installed rebyteai/internet-search in "Step 2: Research & Gather Inspiration" to look up brands, competitor designs, and current design trends on the open web, so the agent will fetch and interpret untrusted public third-party content that can materially influence design decisions and subsequent actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs running runtime installation commands that fetch and execute remote packages—"npx skills add -y nextlevelbuilder/ui-ux-pro-max-skill" and "npx skills add -y anthropics/skills"—which will download and run code from external registries and are required dependencies for the skill.