ghost-report

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to read each secrets finding file "in full" and explicitly inline substantive content (code snippets, remediation commands, and all relevant detail) into the combined report, which forces the LLM to handle and output any secret values verbatim if they appear in those finding files.