google-agents-cli-workflow

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 1 explicitly instructs the agent/user to clone and "study" public samples from GitHub (e.g., the git clone of https://github.com/google/adk-samples) — clearly fetching and ingesting untrusted, user-generated third-party content as part of the required workflow that can influence subsequent design, tooling, and actions.