blucli
Warn
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The 'openclaw' installation metadata specifies downloading and installing a Go module from 'github.com/steipete/blucli/cmd/blu@latest'. This introduces a dependency on external code from a third-party repository that is not directly managed by the skill author.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the 'blu' CLI tool with various arguments to perform discovery, playback control, and configuration of BluOS devices, which involves local system command execution.
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and processing data from external sources (device discovery and TuneIn search results). (1) Ingestion points: Output from 'blu devices' and 'blu tunein search' commands. (2) Boundary markers: None present to distinguish data from instructions. (3) Capability inventory: The agent has the ability to execute shell commands and modify device settings. (4) Sanitization: No sanitization or validation of the external output is performed before it is processed by the agent.
Audit Metadata