baoyu-infographic

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt requires the agent to "preserve all source data verbatim" and to embed the user's source text into analysis, structured-content, and generated prompts/files, so any secrets present in user-supplied content would be included verbatim in outputs (high exfiltration risk).