music-producer-os
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run local Python scripts from the vendor directory (~/agentic-music-producer-os/scripts/) to initialize sessions and record output.
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the interpolation of untrusted user input into shell command arguments. 1. Ingestion points: User-provided titles, emotional briefs, and session data. 2. Boundary markers: Absent; inputs are placed directly in shell arguments. 3. Capability inventory: Shell command execution and browser-based account automation. 4. Sanitization: Absent; there are no instructions for sanitizing or escaping the interpolated data.
Audit Metadata