ziniao-device

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the 'ziniao-cli' binary to manage system-level proxy configurations and perform account-related operations like purchases and renewals. This behavior is consistent with the skill's stated purpose of device management for the Ziniao ecosystem.
  • [PROMPT_INJECTION]: The skill retrieves data from external API endpoints, presenting a surface for indirect prompt injection.
  • Ingestion points: API responses from the 'device list' and generic 'api' commands, as seen in 'SKILL.md' and 'references/ziniao-device-list.md'.
  • Boundary markers: No explicit delimiters or boundary markers are defined to isolate untrusted data from the agent's instructions.
  • Capability inventory: The skill possesses the capability to perform state-changing operations and financial transactions (purchases/renewals) via the CLI tool.
  • Sanitization: The instructions do not include any validation or sanitization steps for the data fetched from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:44 AM