arkcli-billing

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill primary function is executing the arkcli binary to fetch billing and subscription data from Volcengine APIs. This is a legitimate use case for a vendor-provided CLI tool.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the arkcli billing list output. 1. Ingestion points: items array in JSON responses from the billing tool. 2. Boundary markers: Absent for tool output interpolation in prompts. 3. Capability inventory: Restricted to arkcli subcommands and local decimal math. 4. Sanitization: Absent for fields like SplitItemName. The risk is considered low due to the financial nature of the data and structured JSON responses.
  • [DYNAMIC_EXECUTION]: The skill documentation includes examples of generating shell logic using jq and while loops to handle paginated responses. This is a standard and low-risk pattern for managing large API outputs in CLI-based agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:59 PM
Security Audit — agent-trust-hub — arkcli-billing