brainstorming

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 "Research-Driven Exploration" section explicitly instructs the agent to use WebSearch, WebFetch, and Bash/curl to fetch and analyze competitor websites, documentation, and other public web content, which are untrusted third-party sources that the agent will read and use to inform design decisions.