reading-data

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly requires capturing a decision_id (e.g., "TMEM_abc123...") and embedding it verbatim in subsequent tool calls (decision_read/decision_close), which forces the agent to handle and reuse a potentially sensitive token in its outputs/requests, creating an exfiltration risk.