update-model

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to collect or rotate API keys and embed them verbatim into curl headers and JSON payloads (e.g., "Authorization: Bearer $KEY" and "api_key": "<new_key>"), which requires the LLM to output secret values directly and creates an exfiltration risk.