google-agents-cli-workflow

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the user/agent to fetch and read public third-party content (e.g., cloning and studying samples from https://github.com/google/adk-samples and fetching ADK docs via curl https://adk.dev/llms.txt or web searches) as a mandatory Phase 1 step, so untrusted web content can directly influence coding decisions and tool use.