okx-cex-market

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @okx_ai/okx-trade-cli package from the public NPM registry. This package is identified as a vendor-provided resource for the author 'okx' and is necessary for the skill's primary functionality.
  • [COMMAND_EXECUTION]: The skill invokes the okx command-line interface to retrieve market data such as tickers, order books, and technical indicators. These commands are configured for read-only access to public endpoints.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external API responses (market prices, candlestick data, and technical indicators). This ingestion of untrusted data represents a theoretical attack surface, though the risk is minimized by the numerical and structured nature of the data retrieved.
  • Ingestion points: Data enters the context through okx market CLI command outputs (candles, tickers, indicators).
  • Boundary markers: The instructions do not define specific boundary markers for the ingested data.
  • Capability inventory: The skill has the capability to execute shell commands via the okx binary.
  • Sanitization: The CLI tool is responsible for formatting the raw API data, though no additional prompt-level sanitization is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 02:11 PM
Security Audit — agent-trust-hub — okx-cex-market