sonoscli
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill installs the
sonosbinary by fetching a Go module from an external GitHub repository (github.com/steipete/sonoscli/cmd/sonos). While this source is necessary for the skill's primary function, it originates from a third-party developer not explicitly listed in the trusted vendor list. - [COMMAND_EXECUTION]: The skill relies on the execution of the
sonosCLI tool to perform discovery, status checks, and media control on the local network. - [PROMPT_INJECTION]: The skill ingests untrusted data from the local network, such as speaker names and media metadata, which are then presented to the agent.
- Ingestion points: Data returned by
sonos discover,sonos status, andsonos favorites list(SKILL.md). - Boundary markers: Absent; the skill does not instruct the agent to treat output from the tool as untrusted.
- Capability inventory: System command execution via the
sonosbinary and network communication with local speakers (SKILL.md). - Sanitization: Absent; no sanitization or validation of the tool's output is performed before it is used in the agent's context.
Audit Metadata