name-checker

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

• Third-party content exposure detected (high risk: 1.00). The skill's SKILL.md explicitly directs the agent to perform WebSearches of public social media platforms (X/Twitter, Instagram, Facebook, LinkedIn, YouTube, TikTok), public domains, and trademark databases (WIPO, EUIPO, INPI) and to interpret those live third-party pages (e.g., stopping if an exact handle is found), so untrusted external content can directly influence agent decisions and actions.