prompt-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documentation includes links to external installation guides and supplementary skills within the inference-sh and belt-sh GitHub repositories. These resources are consistent with the infrastructure provided by the skill author.
- [INDIRECT_PROMPT_INJECTION]: The skill provides examples of templates that ingest external data, such as code snippets or articles, to be processed by Large Language Models. While this introduces a potential surface for indirect prompt injection, it is a standard use case for a prompting guide and the examples utilize structured JSON input via the CLI tool.
Audit Metadata