arkcli-usage

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill requires and executes the arkcli binary to perform its primary function of querying account usage statistics and plan details.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes structured data from the arkcli utility, which represents a potential surface for indirect prompt injection if the tool output is manipulated.\n
  • Ingestion points: JSON output from arkcli usage stats, usage plan, usage balance, and usage seats subcommands.\n
  • Boundary markers: Absent; the instructions direct the agent to read the tool output directly without delimiters.\n
  • Capability inventory: Execution of the arkcli binary with various parameters to retrieve sensitive account information.\n
  • Sanitization: No explicit sanitization or validation of the CLI output is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:45 AM
Security Audit — agent-trust-hub — arkcli-usage