skills/firecrawl/openclaw/sonoscli/Gen Agent Trust Hub

sonoscli

Warn

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installation instructions specify a remote Go module (github.com/steipete/sonoscli/cmd/sonos@latest) to be downloaded and installed as a binary. This dependency is not from a verified or well-known organization.
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the sonos command-line tool to perform actions on the local network.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from network devices and external music APIs which could contain malicious instructions.
  • Ingestion points: Metadata retrieved from commands such as sonos favorites list, sonos queue list, and Spotify search results (sonos smapi search).
  • Boundary markers: Absent; the skill does not wrap retrieved metadata in delimiters or provide warnings to ignore embedded instructions.
  • Capability inventory: The system performs network discovery via SSDP and communicates with external hardware over the local network.
  • Sanitization: None; music metadata (like track titles or playlist names) is not filtered or escaped before being interpolated into the agent context.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 17, 2026, 07:54 PM
Security Audit — agent-trust-hub — sonoscli