google-cloud-solution-agentic-ai-borderless-data-lakehouse

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

• Third-party content exposure detected (medium risk: 0.65). SKILL.md instructs the agent to “retrieve and read” Google Cloud documentation (public web pages) at runtime to ground its guidance, which can introduce outsider-authored free text via the fetched docs into the LLM context.