customer-success-audit

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt requires the agent to read "actual code" and "reference specific files and lines for every finding" (including analytics/auth/config files), which will likely expose API keys, tokens, or passwords present in those files and thus compel the model to reproduce secret values verbatim in its output.