alibabacloud-yike-cli

CRITICAL E004: Prompt injection detected in skill instructions.

• Potential prompt injection detected (medium risk: 0.30). The skill includes an "Automated Execution Mode" that instructs agents to skip human confirmation and to proceed without blocking on login (attempt commands even if not logged in), which weakens security boundaries and is suspicious steering without clear malicious intent.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow ingests outsider-authored free text via the user’s prompt (natural-language requirements) that is compiled into yike generate image/video command prompts at runtime.