qinghu-video-audio-extract

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill instructs the agent to ask the user for an API key (<密钥>) and use it in a command (qhkit config set --token <密钥>), which risks handling secret values directly in the conversation context and output.

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

• Third-party content exposure detected (low risk: 0.10). The skill processes video platform sharing links using qhkit to parse direct links and extract video metadata or scripts, which can ingest untrusted video titles or descriptions from third-party sites.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of the npm package @iqinghu/qhkit from the public npm registry or mirror, which is a recognized third-party package publisher (common/reputable unofficial tier for npm-hosted packages lacking direct first-party transport authentication).