skills/linkupplatform/openclaw/blucli/Gen Agent Trust Hub

blucli

Warn

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata defines an installation step that downloads a binary using go install github.com/steipete/blucli/cmd/blu@latest. This dependency originates from a third-party repository not associated with the skill author or a trusted vendor, and it is not pinned to a specific version or hash.\n- [COMMAND_EXECUTION]: The skill is designed to interact with the host system by executing the blu command-line tool to perform device discovery, grouping, and playback operations.\n- [PROMPT_INJECTION]: The skill processes data from external media players and third-party services, creating a vulnerability surface for indirect prompt injection.\n
  • Ingestion points: The skill ingests untrusted data from device discovery (blu devices), device status updates (blu status), and search results from external music services (blu tunein search).\n
  • Boundary markers: No delimiters or specific instructions are provided to the agent to distinguish between tool output and instructions, nor to ignore embedded commands within that output.\n
  • Capability inventory: The skill allows the agent to perform network-based control of hardware devices, including volume adjustment, playback control, and device grouping.\n
  • Sanitization: The instructions do not include mechanisms for filtering or sanitizing the output of the blu tool before the agent processes it.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 1, 2026, 08:32 AM
Security Audit — agent-trust-hub — blucli