import-track

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute mv commands that transfer files to their destination. The command parameters are derived from user input and tool outputs from bitwize-music-mcp. This pattern relies on the AI model's ability to properly escape shell metacharacters to prevent command injection.- [PROMPT_INJECTION]: The skill accepts input via $ARGUMENTS for file paths and album names. An attacker could provide paths to sensitive system files (e.g., SSH keys or configuration files) to be moved into the music library structure where they might be exposed.- [PROMPT_INJECTION]: The skill has an indirect injection surface as it processes untrusted markdown files. Ingestion points: Track markdown files read from user-specified locations. Boundary markers: None provided in the instructions. Capability inventory: Includes file reading (Read), shell execution (Bash), and metadata resolution (bitwize-music-mcp). Sanitization: No content validation or sanitization is specified before processing the track files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 11:26 PM