cw-brainstorming

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to perform web searches and include "researched" sources (see references/worldbuilding.md, references/character-development.md, references/chapter-planning.md and others that state "Use web search" or "Search when helpful"), which means it will fetch and interpret content from open/public third-party websites as part of its workflow, exposing it to untrusted user-generated content and potential indirect prompt injection.