netease-music-cli
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes the
ncm-clitool andmpvplayer through shell commands to manage music playback, searches, and configuration. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-generated content and interpolates it into CLI command arguments, creating a potential injection surface.
- Ingestion points: User conversation history and specific keywords are ingested and used in
ncm-cli searchand other commands via the--keywordand--userInputflags as described inSKILL.md(Step 6). - Boundary markers: Absent. The instructions do not define specific delimiters or escaping mechanisms to prevent user input from being interpreted as command flags or secondary instructions by the CLI tool.
- Capability inventory: The skill has the ability to execute shell commands, manage local configuration (storing API keys), and interact with the NetEase Cloud Music API.
- Sanitization: Step 5 provides a manual sanitization step where the agent is instructed to audit user input for sensitive or malicious categories (politics, obscenity, etc.) before proceeding with command execution.
Audit Metadata