unifi-operator

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses common shell utilities including curl, jq, awk, and tr to interact with UniFi controllers. These operations are restricted to a user-defined local host IP or hostname and are necessary for the skill's primary function of managing network infrastructure.
  • [DATA_EXPOSURE]: The skill manages authentication tokens and session cookies for local UniFi OS consoles. It provides mechanisms for handling API keys and session cookies (stored in /tmp/uni.jar), which is standard practice for CLI-based automation tools. No hardcoded credentials or unauthorized data access patterns were found.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data returned from network devices (such as device names, client hostnames, and event logs). While this presents a theoretical attack surface for indirect prompt injection, the risk is assessed as low given the local nature of the data sources and the specific administrative context of the tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 03:17 PM
Security Audit — agent-trust-hub — unifi-operator