generate-test-cases

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly directs the agent to gather and analyze information from third-party sources (e.g., Testomat.io via MCP and the "sync-cases" skill, Jira/Confluence, Figma/Miro, and arbitrary links) and to read/interpret those downloaded pages/files as part of generating test cases, so untrusted user-generated content could materially influence its actions.