google-cloud-solution-agentic-ai-data-science-workflow

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

• Third-party content exposure detected (high risk: 0.85). SKILL.md:69-76 and SKILL.md:121-127 require runtime retrieval of external documentation/resources from public URLs (outsider-authored web content), which would be ingested as readable text into the agent’s LLM context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch and read external documentation and sample code (e.g., https://docs.cloud.google.com/architecture/agentic-ai-data-science.md.txt and https://github.com/google/adk-samples/tree/main/python/agents/data-science) to "ground" guidance, meaning remote content will directly influence generated prompts/instructions.