dpdpa-gdpr-review-parth-desai

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill explicitly instructs the agent to paste the "original clause" verbatim into its redline output, which would force inclusion of any secret values present in the user's document (e.g., API keys, tokens, passwords) into the model's generated output.