unifi-network
Pass
Audited by Gen Agent Trust Hub on Nov 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a secure-by-default model for network management where high-risk operations are disabled unless explicitly enabled via environment variables.
- [SAFE]: All mutations require a two-step confirmation flow, ensuring users can preview and approve changes to network configuration before they are applied.
- [SAFE]: Sensitive information such as VPN keys, WLAN passphrases, and SNMP strings are automatically redacted by the underlying server to prevent accidental exposure.
- [INDIRECT_PROMPT_INJECTION]: Ingestion points: The skill processes data from a network controller (e.g., client hostnames, device names, and event logs) as described in references/network-tools.md. Boundary markers: None explicitly mentioned in the instructions. Capability inventory: Extensive network mutation capabilities including firewall policy creation, VPN server/client management, and routing configuration across 210 tools. Sanitization: The skill describes server-side redaction of sensitive credential fields.
Audit Metadata