recipe-reverse-engineer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The orchestrator explicitly requires passing step outputs "as-is" between agents and generating documentation from code/related files, which will cause any secrets found in the repo or outputs to be forwarded and potentially included verbatim in prompts and generated docs — creating an exfiltration risk.