migrating-python-udfs

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

• Third-party content exposure detected (high risk: 0.75). The workflow’s runtime LLM context is populated from AWS MCP/CLI discovery results (e.g., listing workgroups/clusters and querying pg_proc/python_udf_inventory), which are outsider-authored database content (UDF source/definitions) that the agent reads and then uses for conversion prompts.