homekit
Warn
Audited by Socket on Sep 10, 2026
1 alert found:
AnomalyAnomalySKILL.md
LOWAnomalyLOW
SKILL.md
SUSPICIOUS: the skill’s HomeKit inspection/control scope is largely coherent and includes meaningful safety guardrails, but trust is weakened by the unresolved mismatch between the referenced `homekit` binary and upstream HomeClaw documentation naming `homeclaw-cli`. No clear credential harvesting or third-party exfiltration is described, yet the external CLI/MCP dependency plus real-world actuation capability keeps overall risk at medium.
Confidence: 84%Severity: 57%
Audit Metadata