okx-outcomes
Fail
Audited by Gen Agent Trust Hub on Aug 27, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill downloads and executes an installation shell script from the vendor's GitHub repository (
okx/outcomes-cli) to set up the necessaryokx-outcomesbinary. - [EXTERNAL_DOWNLOADS]: Fetches the
okx-outcomesbinary and related installation assets from the vendor's official GitHub organization resources. - [COMMAND_EXECUTION]: Relies on the execution of shell commands through the
okxandokx-outcomesbinaries to perform all market operations, authentication, and wallet management. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the OKX Outcomes API, creating a potential surface for indirect prompt injection if API fields contain malicious instructions.
- Ingestion points: External data retrieved via
okx outcomes data events,okx outcomes data market, andokx outcomes account positions(SKILL.md, references/data-commands.md). - Boundary markers: Absent; the instructions do not define specific delimiters or guardrails for data ingested from the API responses.
- Capability inventory: Extensive shell execution capabilities through the
okx outcomescommand suite, including on-chain trading and system configuration (SKILL.md, references/clob-commands.md). - Sanitization: Absent; there is no explicit instruction to sanitize or validate data fields before they are incorporated into the agent's context or future commands.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/okx/outcomes-cli/main/install.sh - DO NOT USE without thorough review
Audit Metadata