skills/elizaos/eliza/blucli/Gen Agent Trust Hub

blucli

Warn

Audited by Gen Agent Trust Hub on Mar 17, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's installation process downloads the 'blu' binary via the Go package manager from 'github.com/steipete/blucli/cmd/blu@latest', which is a third-party source not listed among trusted vendors.
  • [COMMAND_EXECUTION]: The skill relies on executing the 'blu' CLI tool to discover and control devices, granting the agent the capability to run system-level subprocesses.
  • [PROMPT_INJECTION]: The skill exposes an indirect prompt injection surface by processing untrusted data from media services and device metadata.
  • Ingestion points: CLI output from 'blu devices' and 'blu tunein search' commands.
  • Boundary markers: Absent; instructions do not specify delimiting external output.
  • Capability inventory: Command execution via the 'blu' binary.
  • Sanitization: Absent; the skill does not appear to sanitize or validate strings returned from the 'blu' tool before processing.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 17, 2026, 07:35 AM