sokosumi

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly tells the agent to "Ask the human for a Sokosumi API key" and even instructs users to "paste it here" and to send "Authorization: Bearer <API_KEY>", which requires the LLM to receive and potentially emit the secret verbatim in requests or outputs.