sonoscli
Warn
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill metadata includes an installation step that fetches and installs a Go module from a third-party repository (
github.com/steipete/sonoscli/cmd/sonos@latest). This source is not associated with the skill author ('insight68') or any pre-approved trusted organizations, representing a supply chain risk. - [COMMAND_EXECUTION]: The skill is designed to execute the
sonosbinary on the host system to discover, control, and query speakers on the local network. - [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection. User-provided strings for speaker names or search queries are interpolated into shell commands (e.g.,
sonos status --name "{user_input}"). This could be exploited to perform command injection if the agent does not properly escape the inputs. - Ingestion points: SKILL.md (user-supplied speaker names and search queries)
- Boundary markers: Absent
- Capability inventory: Subprocess execution of the
sonosCLI tool - Sanitization: Absent
Audit Metadata