sonoscli
Warn
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
sonosbinary usinggo install github.com/steipete/sonoscli/cmd/sonos@latest. This downloads and compiles code from a third-party repository not included in the trusted vendors list. - [COMMAND_EXECUTION]: The skill relies on executing the
sonosbinary to perform its functions, such as discovering devices, controlling playback, and managing groups. This requires the agent to spawn subprocesses. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through data it processes from external sources.
- Ingestion points: The skill reads and processes data from local Sonos speakers (via
sonos status,sonos queue list, andsonos favorites list) and from the Spotify API (viasonos smapi search). - Boundary markers: The instructions do not define clear delimiters or provide 'ignore embedded instructions' warnings for data returned by the CLI tool.
- Capability inventory: The skill has the capability to execute the
sonosbinary with various parameters, potentially influenced by the data it reads. - Sanitization: There is no evidence of sanitization, filtering, or validation of the content returned by the speakers or external APIs before it enters the agent context.
Audit Metadata