yqcloud-deploy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt explicitly suggests using curl with -u username:password if authentication is needed, which instructs embedding credentials verbatim in commands and thus risks secret exposure.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md workflow explicitly fetches chart metadata from a third-party ChartMuseum API (e.g., the curl example "https://chart.choerodon.com.cn/.../api/charts/{chart_name}") and the agent is expected to read those results to choose chart versions and drive deployment actions, exposing it to untrusted external content that could influence decisions.