brand-setup

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow asks users to provide external URLs and competitor URLs ("Step 4: Sample content — 'Share 2-3 URLs or text snippets of content you think nails your brand voice'" and "Step 6: Competitors — 'For each: name, URL...'"), which clearly ingests untrusted public web content that the agent is expected to read and use to shape voice and actions, enabling indirect prompt injection risk.