ziniao-skill-maker

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill documents the use of 'ziniao-cli', a command-line interface tool for interacting with specific APIs. The commands described (e.g., 'ziniao-cli api', 'ziniao-cli zclaw') are standard administrative and operational tools for the platform and are used within the scope of the skill's purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read dependency files such as '../ziniao-shared/SKILL.md'. This is a structural requirement for modular skill design within the vendor's ecosystem and does not constitute a malicious injection surface.
  • [SAFE]: No obfuscation, hardcoded credentials, remote code execution patterns, or unauthorized data exfiltration techniques were detected. The skill uses standard markdown and instructional language to guide the creation of new skills.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 03:44 PM
Security Audit — agent-trust-hub — ziniao-skill-maker