brand-alchemy

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

• Third-party content exposure detected (high risk: 0.70). The skill's mandatory Step 4 instructs the agent to run scripts/domain_checker.py which performs DNS lookups and fetches RDAP data from rdap.org (public third-party internet sources) and the agent must read/interpret those external responses to determine domain availability and drive naming decisions.