skills/bankrbot/skills/suwappu-dex/Gen Agent Trust Hub

suwappu-dex

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill registers an external MCP server from the vendor's domain at https://api.suwappu.bot/mcp. This connection is used to dynamically load and execute the skill's tool definitions.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources such as blockchain providers and DeFi protocols, creating a surface for indirect prompt injection.
  • Ingestion points: Data is received through tools like get_quote, get_prices, get_portfolio, and predict_markets.
  • Boundary markers: The skill instructions do not include specific delimiters or warnings to ignore instructions that might be embedded in the external market data.
  • Capability inventory: The skill has the capability to execute financial transactions via execute_swap, though this is excluded by default in the setup instructions.
  • Sanitization: No evidence of input validation or sanitization is provided for the data returned from the 10+ external providers (e.g., Li.Fi, CoW Protocol, Jupiter).
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 08:46 AM
Security Audit — agent-trust-hub — suwappu-dex