sonoscli
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads and installs the
sonoscliGo module from an external GitHub repository (github.com/steipete/sonoscli) during installation. - [COMMAND_EXECUTION]: The skill executes the
sonosbinary on the host system to perform network discovery, device status checks, and media control operations. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted data from local network devices and external service APIs (like Spotify search results).
- Ingestion points: Data returned by
sonos status,sonos favorites list, andsonos smapi searchas described inSKILL.md. - Boundary markers: Absent; no delimiters are used to separate retrieved data from agent instructions.
- Capability inventory: The skill has the ability to execute system commands via the
sonosCLI. - Sanitization: Absent; there is no evidence of filtering or validation of the content retrieved from external sources before it is presented to the agent.
Audit Metadata