h3-prompt-writing
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security threats or malicious patterns were identified during the analysis. The skill consists of instructional markdown files and text-based reference guides for prompt construction.
- [NO_CODE]: The skill package contains no executable scripts (Python, JavaScript, Shell), binary files, or configuration for external tool execution. All provided files are documentation and templates.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a framework for processing untrusted user input (video generation requirements). It mitigates potential risks by prescribing the use of strict structural markers such as shot labels, dedicated field names (e.g., integrated_multimodal_description), and dialogue-specific tags like
<d>. These act as natural boundaries that help separate instruction from data during prompt generation.
Audit Metadata