linkpix-video-audio-extract

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 embed it into a command line instruction (qhkit config set --token <密钥>), which is an insecure credential handling pattern.

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

• Third-party content exposure detected (low risk: 0.10). The workflow processes video platform share links and metadata (like video scripts) via qhkit, which ingests outsider-authored content from public video platforms.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the installation and execution of an npm package (@iqinghu/qhkit) from the public npm registry to parse video links during runtime, representing a common unofficial operational dependency.