alibabacloud-openclaw-ecs-dingtalk

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill requires collecting full secret values (Bailian API key, DingTalk client secret), recording them, and embedding them (even if base64-encoded) directly into generated RunCommand command content, so the agent must handle and output secrets verbatim.

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 4 RunCommand explicitly curls and executes a public install script (https://openclaw-install-scripts.oss-cn-hangzhou.aliyuncs.com/install.sh) on the ECS instance (and earlier steps also fetch external setup scripts like deb.nodesource.com), meaning the agent fetches and acts on untrusted third-party content that can change behavior.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill executes remote scripts at runtime via Cloud Assistant — e.g., it pipes https://deb.nodesource.com/setup_22.x to bash and downloads then executes https://openclaw-install-scripts.oss-cn-hangzhou.aliyuncs.com/install.sh — both fetch and run remote code as required dependencies.