linkpix-wanx-3-clone

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill prompt instructs the agent to ask the user for an API key/token and then directly execute a command embedding that token as a command-line argument (qhkit config set --token <密钥> --env prod). This pattern exposes credentials through the LLM context and output.

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests outsider-submitted video URLs and fetches external video content via video-inspire generate for analysis, but this takes structured URLs rather than unvetted free text feeds or monitored communications.