skills/product-on-purpose/thinking-framework-skills/think-decision-option-review/Gen Agent Trust Hub
think-decision-option-review
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and templates that guide the AI agent through a decision-making process. It does not include any executable scripts, binaries, or commands that interact with the underlying system.
- [NO_CODE]: No software dependencies, package installations (npm/pip), or remote code execution patterns were detected. The functionality is implemented purely through prompt engineering and structured templates.
- [INDIRECT_PROMPT_INJECTION]: The skill acts on user-provided input (options and criteria), creating a surface for indirect prompt injection. However, because the skill has no functional capabilities—such as network exfiltration, file system access, or command execution—the risk associated with this ingestion is negligible. The instructions mandate the use of a specific markdown template (
references/TEMPLATE.md), which provides a clear output boundary.
Audit Metadata