openhue
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to execute the
openhuecommand-line utility. This allows the agent to list lights and rooms, and to modify their state (on/off, brightness, color) via a Hue Bridge. - [EXTERNAL_DOWNLOADS]: The skill defines an automated setup process using the Homebrew package manager to download and install the
openhue-clifrom its official GitHub tap (openhue/cli/openhue-cli). - [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection if an attacker can control names on the user's Hue Bridge.
- Ingestion points: Data enters through the output of discovery commands like
openhue get lightandopenhue get roomas documented in SKILL.md. - Boundary markers: The skill does not implement delimiters or instructions for the agent to ignore embedded instructions in the command output.
- Capability inventory: The skill includes write capabilities to change device states using the
openhue setcommand as documented in SKILL.md. - Sanitization: No sanitization or escaping of device names is performed before they are processed by the agent.
Audit Metadata