maestro-analyze

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs agents to extract and append code snippets and findings (file:line, 20–50 line snippets, discoveries.ndjson and findings fields) which will cause the LLM to output verbatim file contents and thus any secrets embedded in those files.