skills/product-on-purpose/thinking-framework-skills/think-evidence-vs-inference-sort/Gen Agent Trust Hub
think-evidence-vs-inference-sort
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill processes external content (prompts, documents, or conclusions) to classify claim types. This constitutes an indirect prompt injection surface; however, the skill lacks execution capabilities (no tools or shell commands are used), and its primary function is categorization rather than action, making this surface benign in context.
- [SAFE]: The skill references a GitHub repository (
github.com/product-on-purpose/thinking-framework-skills) belonging to the identified author. This reference is used for documentation and attribution purposes and does not involve remote code execution or data exfiltration.
Audit Metadata