tutorial
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands via the Bash tool to create directory structures (e.g.,
mkdir -p {content_root}/artists/[artist]/...). These commands rely on variables derived directly from interactive user input. - [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where untrusted data (user-provided artist and album names) is ingested and used to perform privileged filesystem operations. \n
- Ingestion points: User responses during the interactive tutorial phase in
SKILL.md. \n - Boundary markers: Absent; there are no instructions to the agent to validate or escape characters like
..or shell metacharacters before usage. \n - Capability inventory:
Bash,Write,Edit,Read, andbitwize-music-mcp. \n - Sanitization: No sanitization or validation logic is specified for the input processed from the user.
- [DYNAMIC_EXECUTION]: The skill dynamically assembles shell commands at runtime by interpolating user-provided strings into path templates. While used for routine directory creation, this pattern is inherently risky when processing unvalidated external input.
Audit Metadata