unifi-network

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from the UniFi network environment, creating a potential surface for indirect prompt injection.
  • Ingestion points: Data is retrieved through tools such as unifi_list_clients and unifi_list_events (in references/network-tools.md), which provide user-controlled strings like client hostnames and event descriptions to the agent.
  • Boundary markers: There are no specified delimiters or instructions to the agent to treat data from the controller as untrusted or to ignore embedded commands.
  • Capability inventory: The skill allows for high-impact network changes, such as modifying firewall rules, port forwarding, and rebooting devices (as seen in references/network-tools.md).
  • Sanitization: No sanitization or validation of the data pulled from the network is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 10:44 AM
Security Audit — agent-trust-hub — unifi-network