naming

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent (Task agent: arc:research:naming) to check GitHub for popular repos, check domain availability, and "search for existing products" — i.e., fetch and interpret public GitHub and web content (untrusted, user-generated) as part of its workflow, which can influence naming decisions.