workflow-test-fix

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

• Third-party content exposure detected (high risk: 0.90). The skill instructs its context-search/test-context agents to incorporate "Web examples (use Exa MCP for unfamiliar tech/APIs)" into the multi-source context discovery and to synthesize those web-derived findings into the session context/package (phases/02-test-context-gather.md and B.3), meaning the agent will fetch and interpret external/public web content that can influence planning and fix-generation actions.