hue-lights

Warn

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the openhue-cli via a third-party Homebrew tap (openhue/tap/openhue-cli). This introduces a software dependency from a source that is not on the pre-approved trusted list.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it retrieves data from local network devices which could be manipulated to include malicious instructions.
  • Ingestion points: Data is ingested via openhue get lights, openhue get rooms, and openhue get scenes commands in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded content within retrieved names.
  • Capability inventory: The skill uses the Bash tool to perform operations such as openhue set which can be influenced by the ingested data.
  • Sanitization: The skill lacks instructions for sanitizing or validating names retrieved from the Hue Bridge before using them in further shell commands.
  • [COMMAND_EXECUTION]: The skill relies on the Bash tool to execute a series of commands for managing smart lights and discovery. This includes a setup phase (openhue setup) that creates and stores credentials in the ~/.config/openhue/ directory.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 7, 2026, 02:13 AM