generate-cases

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

• Third-party content exposure detected (high risk: 0.80). The skill's Workflow / "Information Sources" and Step 1 explicitly require the agent to gather and analyze content from external links and third‑party systems (e.g., Jira, Confluence, Figma, Miro, Testomat.io and "links or via MCP tools"/"sync-cases" to download tests), which are user-generated or public sources the agent will read and use to drive its next actions.