Hive Home
Analysis
The skill appears to do what it says, but it can use Hive credentials and persistent device keys to change home heating and hot-water settings, so it deserves careful review before installation.
Findings (3)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.
session.heating.setTargetTemperature(zone, args.temp) ... session.hotwater.setMode(hw, args.mode.upper())
These are direct state-changing calls for home heating and hot water. The artifacts do not include an approval requirement or safety limits before the agent runs these mutations.
Source: unknown; Homepage: https://github.com/yourusername/agent-skills
The published source provenance is unclear and the homepage appears placeholder-like for a skill that requires smart-home account credentials. The docs also rely on a third-party unofficial API library.
Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.
For automation (no 2FA each run): `HIVE_DEVICE_GROUP_KEY`, `HIVE_DEVICE_KEY`, `HIVE_DEVICE_PASSWORD` ... print("Store for device login:", device_data)The skill uses persistent device credentials that bypass repeated 2FA, and the example prints those credentials to output for storage. In an agent or logged terminal, that can expose reusable account/device access.
