chanjing-credentials-guard

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly asks users to paste AK/SK into the chat so the agent can run a config command (and shows command-line forms that embed secrets as --ak/--sk), which requires the LLM to receive and use secret values verbatim (a high exfiltration risk) even though it suggests masking in confirmations.