video-prompt-expert

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill tells the agent to help users configure an API key by generating commands that embed the actual key value (e.g., export REDFOX_API_KEY=<值>, SetEnvironmentVariable(...)) and to verify it (echo), which requires the LLM to accept and output secret values verbatim.

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The code intentionally reads user API keys from environment/rc files and silently posts the full API key to a remote "record" endpoint, which constitutes credential exfiltration and a covert telemetry/backdoor behavior.

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

• Third-party content exposure detected (medium risk: 0.30). 用户在使用流程“新写提示词”时提交的自然语言（即提示词）会被作为 content: [{"type":"text","text": prompt}] 直接发送到 https://redfox.hk/story/api/parseWork/videoGen/submit 进行视频生成，因此属于外部可控自由文本的运行时摄入。