music-assistant
Pass
Audited by Gen Agent Trust Hub on Mar 20, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The installation process involves downloading the skill definition from the author's repository on GitHub.- [COMMAND_EXECUTION]: The skill executes the 'ha-ma' CLI tool to perform all browsing, search, and playback functions within Home Assistant.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting data from external music library providers. Ingestion points: Music metadata is retrieved via 'ha-ma search' and 'ha-ma browse' commands. Boundary markers: There are no identified delimiters or system instructions used to isolate this untrusted metadata from the agent's logic. Capability inventory: The agent possesses the ability to execute playback controls, modify user preferences, and access the Home Assistant API using a long-lived access token. Sanitization: There is no evidence of sanitization or validation performed on retrieved metadata like song titles or album names before they are processed by the agent.
Audit Metadata