lifi-mcp-skill
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructions direct the agent to connect to the LI.FI MCP endpoint at
https://mcp.li.quest/mcp. This is a well-known service used for cross-chain liquidity and bridge discovery. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data (such as route details, token metadata, and bridge connections) fetched from the LI.FI API. This data is ingested into the agent's context during execution, presenting a standard indirect prompt injection surface common to tools that interact with external web services. This surface is documented as follows:
- Ingestion points: Data is fetched via
uxcfromhttps://mcp.li.quest/mcp(documented inSKILL.md). - Boundary markers: None identified in the prompt templates.
- Capability inventory: The skill uses the
uxctool for network queries and local command linking. - Sanitization: Relies on default agent guardrails and the structured nature of the MCP response data.
Audit Metadata