repo-architecture
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, defining a decision protocol for where to store files based on their primary subject.
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes read-only tools such as
search,get_page, andlist_pagesto access repository content. While these tools ingest data from the repository, the skill lacks the capability to execute commands or write to the filesystem based on that data, and it is explicitly marked as non-mutating.
Audit Metadata