ucp-split-payments

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch live specifications from ucp.dev using WebSearch and WebFetch tools. It also references a GitHub repository for sample implementations at github.com/Universal-Commerce-Protocol/samples. These resources are directly related to the skill's primary function of implementing the UCP Split Payments extension.
  • [INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from external web sources (documentation and search results). While this creates a theoretical surface for indirect prompt injection if the external content were malicious, the instructions focus on technical specifications for code implementation, and no exploitation of this surface is present in the skill itself.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 06:33 PM