testcontainers-go

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

• Third-party content exposure detected (high risk: 0.80). The skill's instructions and examples explicitly pull and run public Docker images (e.g., "postgres:16-alpine", "nginx:alpine", "alpine:latest", and "confluentinc/..." in SKILL.md and examples) and read/exec into container logs, HTTP endpoints, and files (wait.ForLog, wait.ForHTTP, Exec, Logs, Endpoint, CopyFileFromContainer), meaning it ingests untrusted third‑party content from public registries and containerized services that the workflow expects the agent to read and act on.