arkcli-models
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a legitimate administrative extension for the Volcengine Ark platform. It instructs the agent on how to use the
arkclicommand-line tool to query model metadata, pricing, and performance stats. - [COMMAND_EXECUTION]: The script contains templates for executing shell commands and using
jqfor JSON processing to parse model IDs and metadata. These are standard developer operations for integrating CLI outputs and do not involve arbitrary or dangerous command injection from untrusted sources. - [INDIRECT_PROMPT_INJECTION]: While the skill processes external model metadata from the Volcengine API, it includes strict instructions for data validation, the use of
jqfor structured parsing, and explicit "hard gates" to prevent the agent from misinterpreting data as instructions. The potential attack surface is handled with best practices. - [DATA_EXFILTRATION]: No evidence of sensitive data exfiltration was found. All network-related operations are performed through the authenticated
arkclitool and target official Volcengine domains (volcengine.com) in accordance with the author's identity. - [OBFUSCATION]: No obfuscated content, hidden characters, or encoding tricks (such as Base64 or hex) were detected in the instructions or reference materials.
Audit Metadata