aps-doc-ingestion

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill mandates extracting "real, extracted data" and "working examples from actual configs" (including connection parameters, JDBC strings, service account files and credential references) from code/config files, which can require the LLM to include secret values verbatim and thus poses a high secret-exfiltration risk despite a note saying "WITHOUT exposing secrets".