branding-assessment

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

• Third-party content exposure detected (high risk: 0.90). The skill's Procedure step 2 ("Fetch each surface") explicitly fetches public, user-generated content — website home/about pages, GitHub profiles and README of pinned repos, Hugging Face profiles/activities, and publicly-accessible LinkedIn activity — and then requires the agent to read and use that content to score surfaces and produce actionable recommendations, so untrusted third-party content can materially influence decisions.