1inch-market-data
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill utilizes an authenticated platform tool (
product_api) and accesses local configuration files (file://1inch-mcp/guides/api-index) that are standard for the 1inch agent environment. No evidence of prompt injection, data exfiltration, or unauthorized command execution was found. - [INDIRECT_PROMPT_INJECTION]: The skill functions by ingesting external market data, which is an inherent vector for indirect prompt injection. 1. Ingestion points: JSON responses from
product_apitool calls defined inreferences/RECIPES.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill is restricted to calling theproduct_apitool. 4. Sanitization: No explicit validation or filtering of market data fields is described in the instruction files.
Audit Metadata