gate-exchange-assets

Pass

Audited by Gen Agent Trust Hub on Mar 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill correctly maps user intents to specific read-only MCP tools for asset and balance queries. The 'read-only' guarantee is reflected in the provided tool mapping, which excludes any order placement or transfer capabilities.\n- [PROMPT_INJECTION]: The skill processes financial data from the Gate Exchange API, which represents a surface for indirect prompt injection. However, given the skill's primary purpose and restricted read-only capabilities, this is considered a standard operational risk.\n
  • Ingestion points: Data enters the agent context through responses from Gate Exchange MCP tools (e.g., cex_wallet_get_total_balance, cex_spot_get_spot_accounts) as specified in SKILL.md.\n
  • Boundary markers: No explicit delimiters are used for external API data in the prompts.\n
  • Capability inventory: The skill is strictly limited to read-only asset and ledger queries; it contains no tools for order placement, transfers, or code execution.\n
  • Sanitization: The skill follows standard handling of API responses with no additional sanitization or filtering layer specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 13, 2026, 11:39 AM