htx-mark-price

Pass

Audited by Gen Agent Trust Hub on Jun 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the htx-cli tool to fetch market data. User-controlled parameters such as contract_code, period, and size are interpolated directly into shell command strings (e.g., htx-cli futures call GET ... --query contract_code=<code>&period=<period>&size=<N> --json). This pattern creates a risk of command injection if the input is not properly sanitized by the underlying shell or the tool itself.\n- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it processes untrusted user input to drive system actions.\n
  • Ingestion points: User queries for contract codes and timeframes in SKILL.md.\n
  • Boundary markers: Absent; there are no instructions to validate or escape user input before interpolation.\n
  • Capability inventory: Execution of shell commands via the htx-cli binary.\n
  • Sanitization: No validation or sanitization steps are defined for the input parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 12, 2026, 08:49 PM
Security Audit — agent-trust-hub — htx-mark-price