pr
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely instructional and provides templates for text generation. It does not contain any executable scripts, command-line operations, or network requests.
- [INDIRECT_PROMPT_INJECTION]: The skill references an external file (
GLOSSARY.md) as a source for domain language. While this is a data ingestion point, the skill possesses no dangerous capabilities (such as file writing, network access, or shell execution) that could be exploited via malicious content in the glossary. - [EXTERNAL_DOWNLOADS]: The skill mentions external GitHub repositories for attribution in the
CREDITS.mdfile (Humanlayer/Dex Horthy). These are documented for reference and do not involve any automated downloads or executions during the skill's operation.
Audit Metadata