okx-cex-smartmoney

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, including trader leaderboards and nickname search results, which can be controlled by external actors and potentially contain malicious instructions.\n
  • Ingestion points: Trader nicknames and performance data ingested via smartmoney traders-by-filter, search-trader, and trader-positions (SKILL.md, references/trader-commands.md).\n
  • Boundary markers: The skill instructions do not specify any delimiters or safety markers for the agent to use when interpreting this external data.\n
  • Capability inventory: The skill is primarily read-only, using the okx CLI to fetch data.\n
  • Sanitization: No sanitization of external nicknames or trader-supplied text is mentioned.\n- [COMMAND_EXECUTION]: All primary functions of the skill rely on executing commands through the okx CLI tool.\n- [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @okx_ai/okx-trade-cli package from npm. This package is an official vendor resource provided by the author 'okx'.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 12:07 PM