swap-tokens

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFE
Full Analysis
  • [Indirect Prompt Injection] (SAFE): The skill uses user input for token names and amounts in bash commands, which is the intended functionality of the tool.
  • Ingestion points: User-specified parameters for chainKey, tokenIn, tokenOut, and amount in the 'fdx call swapTokens' command.
  • Boundary markers: Delimiters are not explicitly used in the prompt instructions, but the tool access is restricted.
  • Capability inventory: Tool usage is strictly limited to the 'fdx' command-line utility via specific allowed-tools glob patterns (status, swapTokens, getWalletOverview).
  • Sanitization: The skill relies on the 'fdx' tool and the agent's execution environment to handle parameter validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:45 AM