god

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly ingests and acts on external, user-generated content from third-party services (e.g., "spec" and other steps "busca dados em Jira/Figma" in SKILL.md and code-like-me Phase 1 which fetches tasks from Jira via the Atlassian MCP and Figma via the Figma MCP), and that fetched content is read and used to drive planning, implementation, publishing, and tool actions—so untrusted third‑party content can materially influence agent behavior.