planetscale

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks the user to paste the service token ID and token and then constructs a shell command that embeds those secrets as literal command-line arguments (ruby ... 'PASTED_TOKEN_ID' 'PASTED_TOKEN'), which requires the LLM to handle and output secret values verbatim.