aprende

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read full conversation transcripts and optionally include short verbatim "source_excerpt" and to write conversation-derived content to disk (without any redaction rules), so if secrets appear in the transcript the LLM may be required to reproduce them verbatim, creating an exfiltration risk despite confirmation steps.