linkpix-video-audio-extract

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions involve executing shell commands for media processing and tool management, which provides a surface for command injection if inputs are not properly escaped by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill downloads the ffmpeg binary via system package managers and the @iqinghu/qhkit library from the public NPM registry.
  • [PRIVILEGE_ESCALATION]: The recommended installation commands for system-level dependencies (e.g., apt-get install) require elevated privileges to modify the host environment.
  • [INDIRECT_PROMPT_INJECTION]: (1) Ingestion points: Video metadata and scripts are retrieved from external platform links via the qhkit tool. (2) Boundary markers: The skill does not define clear boundaries or markers to isolate potentially untrusted external content. (3) Capability inventory: The skill has access to shell command execution (ffmpeg, qhkit) and file system operations. (4) Sanitization: There is no evidence of sanitization or safety checks performed on data fetched from external sources before it is processed or presented.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 04:09 PM