pionex-earn-arbitrage

Pass

Audited by Gen Agent Trust Hub on Jul 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @pionex/pionex-ai-kit package via NPM to provide the pionex-trade-cli utility. This package is managed by the verified vendor and is necessary for the skill's functionality.
  • [COMMAND_EXECUTION]: The skill executes shell commands using pionex-trade-cli to fetch products and manage arbitrage positions. It mitigates risk by requiring a --dry-run and explicit user approval before executing any investment or withdrawal commands.
  • [PROMPT_INJECTION]: The skill ingests untrusted data from external Pionex API endpoints, which creates a surface for indirect prompt injection.
  • Ingestion points: API responses from fetchProducts and fetchUserBalances in SKILL.md.
  • Boundary markers: None. The skill does not utilize specific delimiters or instructions to ignore potential commands within the API data.
  • Capability inventory: The agent can perform financial transactions (stake/unstake) and read account information using CLI tools.
  • Sanitization: None. The skill lacks instructions for sanitizing or validating the content retrieved from the API.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 27, 2026, 08:16 AM
Security Audit — agent-trust-hub — pionex-earn-arbitrage