sokosumi

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). This skill explicitly instructs the agent to ask the user for an API key and pass it directly into CLI flags or auth-token arguments (e.g., --api-key "$KEY", --auth-token "$COWORKER_TOKEN"), which requires the LLM to handle and potentially output the secret verbatim.