code-change-summarizer

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This prompt instructs the model to read and reproduce code diffs, before/after snippets, configuration and request bodies (e.g., env vars, auth examples), so if those inputs contain real API keys or passwords the model may be required to output them verbatim, creating an exfiltration risk.