qinghu-video-audio-extract
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user or agent to install the
@iqinghu/qhkitpackage from the npm registry. It also suggests the use of thenpmmirror.comregistry, which is a well-known service providing a mirror of the official npm registry. - [COMMAND_EXECUTION]: The skill utilizes the
ffmpegCLI tool for local audio extraction and theqhkitCLI for processing remote video links. These are standard tools for the stated purpose of the skill. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of video files and URLs provided by the user.
- Ingestion points: Video URLs from social platforms and local video file paths.
- Boundary markers: None present in the instructions.
- Capability inventory: Includes shell command execution via
ffmpegandqhkit, file system writes for the output MP3/WAV files, and network access to fetch video content. - Sanitization: None explicitly defined; the skill relies on the agent's safe execution of shell commands.
Audit Metadata