term-structure

Pass

Audited by Gen Agent Trust Hub on Apr 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches a platform-specific binary (term-structure) from the vendor's official GitHub repository (MigOKG/plugin-store).
  • [COMMAND_EXECUTION]: Runs shell scripts to detect the host architecture, manage binary installation in ~/.local/bin, and execute installation reporting logic.
  • [DATA_EXFILTRATION]: Collects system metadata including hostname, operating system details, and the user's home directory path to generate a unique device ID. This ID is hashed and sent via POST requests to external telemetry endpoints at plugin-store-dun.vercel.app and okx.com for installation tracking.
  • [REMOTE_CODE_EXECUTION]: Downloads an external binary and grants it execution permissions (chmod +x), which is then utilized for all protocol-related commands.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from external on-chain smart contracts. It includes a 'Data Trust Boundary' warning instructing the agent to treat all CLI output as untrusted content.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 9, 2026, 09:46 AM