agency-multi-platform-publisher

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt explicitly shows and instructs embedding browser cookies/API credentials (e.g., sessdata, bili_jct, buvid3) into code/commands and tells users to copy cookies from F12, which requires the LLM to handle/output secret values verbatim.