ollama-review

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill reads repository diffs and untracked files into the model prompt and then returns the Ollama model's output verbatim (including contextual code snippets), which can cause any secrets present in those files to be emitted by the LLM — creating an exfiltration risk.