amazon-bedrock

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

• Third-party content exposure detected (high risk: 0.90). The skill's required KB/RAG workflows explicitly ingest and query untrusted third-party content (e.g., data_source_type: "web_crawler" in references/knowledge-bases-setup.md and RetrieveAndGenerate usage in references/knowledge-bases-retrieval.md referenced from SKILL.md), and those retrieved chunks are incorporated into prompts and agent actions, enabling indirect prompt injection.