h3-ref-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill functions as a pure text-formatting and prompt engineering template. It provides a structured methodology for converting user ideas and media references into a six-section brief.
- [SAFE]: No indicators of malicious activity were found. There are no command executions, network requests, hardcoded credentials, or obfuscated sections within the instructions.
- [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface in Category 8 as it ingests untrusted user input (ideas and media descriptions). However, the skill does not use any tools or possess capabilities (such as file system access or network operations) that could be exploited through such an injection. The instructions are focused on data mapping and formatting, which significantly limits the risk.
Audit Metadata