arkcli-models

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill facilitates legitimate interaction with the Volcengine Ark platform. It focuses on model catalog search, selection, and activation using established CLI tools.
  • [COMMAND_EXECUTION]: Provides a Python script template in documentation for local data processing. The script is used to filter model metadata by creation time and type when server-side filters are not available. It uses standard library modules (json, datetime) and operates on local JSON output from the CLI.
  • [PROMPT_INJECTION]: As the skill processes external model metadata such as descriptions and tags, it possesses an indirect prompt injection surface. However, the instructions emphasize using structured JSON format and specific search flags to maintain data integrity.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 08:29 AM
Security Audit — agent-trust-hub — arkcli-models