openhue

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill configuration specifies the installation of the openhue-cli tool via Homebrew from the openhue/cli/openhue-cli repository tap.
  • [COMMAND_EXECUTION]: The skill executes shell commands using the openhue binary (SKILL.md) to communicate with and control Philips Hue Bridge hardware on the local network.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes untrusted user data without sufficient safeguards.
  • Ingestion points: User-provided light, room, and scene names are used directly in command arguments in SKILL.md.
  • Boundary markers: There are no markers or instructions to isolate user input from the rest of the command string.
  • Capability inventory: The skill possesses the capability to execute shell commands with the openhue binary as seen in SKILL.md.
  • Sanitization: No input validation or escaping is applied to ensure that user-provided names do not contain shell metacharacters or additional commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 12:13 AM