recipe-eval-prompt

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The orchestrator explicitly passes the user's exact request through to analyzers and requires presenting both the original and optimized prompts "in full" (including result.final_prompt), so any secrets contained in the user's input would be echoed verbatim by the system and exposed in outputs.