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 Jun 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill processes untrusted user data (documents, prompts, or conclusions) as its primary function. While this creates a theoretical surface for indirect prompt injection, the skill lacks any dangerous capabilities (such as network access, file system writes, or command execution) that could be exploited.
- Ingestion points: Processes user-provided text via the instructions in
SKILL.md. - Boundary markers: No explicit delimiters or 'ignore' instructions are defined for the input text.
- Capability inventory: No scripts or subprocess calls are present across any of the files; the skill only generates a markdown table.
- Sanitization: No sanitization of input data is performed.
- [SAFE]: References the author's official GitHub repository
github.com/product-on-purpose/thinking-framework-skillsin the file headers for metadata and attribution purposes.
Audit Metadata