unifi-security-tools
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines tools that ingest data from external UniFi controller APIs and perform sensitive operations, creating an attack surface for indirect prompt injection.
- Ingestion points: Tools such as
list_firewall_rules,list_firewall_policies,list_traffic_matching_lists, andlist_radius_profilesread data from a UniFi controller (local or cloud-connected). - Boundary markers: The documentation does not specify the use of delimiters or instructions to ignore embedded commands when processing external API data.
- Capability inventory: The skill includes high-privilege capabilities such as
create_firewall_rule,update_firewall_policy,delete_firewall_group,create_acl_rule, andconfigure_guest_portal. - Sanitization: While the skill uses models for data validation, the documentation notes that these models are intentionally permissive (
extra="allow") and that lockout protection is "thin," relying primarily on manual review and dry runs.
Audit Metadata