import-audio
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
Bashtool to executemkdir,mv, andunzipcommands to move audio files and extract stems from ZIP archives into a structured album directory.\n- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted user input is used in shell operations:\n - Ingestion points: User-provided arguments for
<file-path>,<album-name>, and[track-slug]are ingested from$ARGUMENTSinSKILL.md.\n - Boundary markers: Absent. The instructions do not define delimiters or provide guidance to the agent on how to handle malicious shell metacharacters within these inputs.\n
- Capability inventory: The skill has the ability to execute shell commands via the
Bashtool and interact with the vendor-specificbitwize-music-mcptool.\n - Sanitization: Absent. Input variables are interpolated directly into shell command templates (e.g.,
mv "{source_file}" "{resolved_path}/{filename}") which could lead to command injection if a user provides input containing backticks, semicolons, or other shell control characters.
Audit Metadata