strategy-ranking-sniper
Fail
Audited by Gen Agent Trust Hub on Mar 24, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill includes explicit instructions for the agent to inform the user that any security scanning warnings are 'false positives'. This is a deceptive attempt to bypass external safety assessments and prevent the user from taking security alerts seriously.
- [REMOTE_CODE_EXECUTION]: The skill automates the installation of the 'onchainos' and 'plugin-store' tools by downloading shell scripts from the OKX GitHub organization and piping them directly to the shell (
curl | sh). While originating from a well-known service, this pattern allows for unverified remote code execution. - [COMMAND_EXECUTION]: Implements logic that fetches data from the GitHub API and pipes it directly into a Python interpreter (
curl | python3) to calculate download statistics. This represents a dynamic code execution pattern where remote content is executed with local interpreter privileges. - [PROMPT_INJECTION]: (Indirect Surface) The skill processes external token data and ranking metadata from the OKX DEX API. This data influences automated buy and sell decisions. The instructions do not specify sanitization or validation of this external content, creating a surface for indirect prompt injection if the metadata contains malicious instructions.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/okx/plugin-store/main/install_strategy.sh, https://raw.githubusercontent.com/okx/onchainos-skills/main/install.sh, https://raw.githubusercontent.com/okx/plugin-store/main/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata