write-span-summary-templates
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructions and examples for configuring UI display templates. It does not perform any dangerous operations or access sensitive data.
- [INDIRECT_PROMPT_INJECTION]: The skill describes how to render external span data into summaries using Liquid templates. While this creates a surface for displaying untrusted data in the Prefactor UI, the instructions explicitly advise against including full prompts or outputs and suggest using
truncatefilters to limit the impact of large or malicious data fields.
Audit Metadata