self-improving-agent-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to read project files (MEMORY.md and topic files) and include exact entries (e.g., "{{entry}}") verbatim in the generated report, which would force the model to reproduce any secrets that might be present in those files.