1inch-wallet-data
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest user-supplied data such as blockchain wallet addresses and token symbols to perform API lookups. This creates a standard surface for indirect prompt injection where malicious input could be supplied via external data, though the risk is minimized by the skill's use of structured API parameters.
- Ingestion points: Wallet addresses, token symbols, and chain IDs provided by the user in
SKILL.mdandreferences/RECIPES.md. - Boundary markers: None explicitly defined in the instructions to delimit user data from system instructions.
- Capability inventory: The skill utilizes the
product_apitool (network access toapi.1inch.com), asearchtool, and reads local documentation files (file://1inch-mcp/guides/api-index). - Sanitization: No explicit sanitization or validation logic is defined within the prompt instructions.
- [DATA_EXPOSURE]: The skill accesses wallet holdings and transaction history, which is appropriate and necessary for its documented purpose as a portfolio management and wallet data tool. The network requests are directed to official vendor endpoints (
api.1inch.com).
Audit Metadata