h3-prompt-writing
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is composed entirely of markdown and text files containing formatting instructions, examples, and prompt templates. It does not include any scripts (Python, JavaScript, Shell) or binaries.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided multimodal descriptions to transform them into a specific prompt structure. Although this involves processing untrusted data, the risk is mitigated by the use of strict structural delimiters like
<d>tags for dialogue and[Shot N]markers for scene transitions. Furthermore, the skill has no functional capabilities—such as network access, file writing, or command execution—that could be exploited via injection.
Audit Metadata