aiconfig-custom-metrics

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill instructs the agent to detect or ask for LaunchDarkly API tokens (including reading ~/.claude/config.json or prompting the user) and then embeds that token directly into Authorization headers/requests, which requires the LLM to handle secret values verbatim.