arch-v
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text to generate video prompts for external models. It employs a multi-stage validation framework (detailed in references/validation-rules.md) that checks for mandatory components, internal consistency (e.g., time/weather conflicts), and technical feasibility. This structured approach provides a clear boundary and sanitization layer for user-provided data.
- [NO_CODE]: The skill consists entirely of Markdown instructions and configuration. It does not contain executable scripts, binaries, or automated network operations.
Audit Metadata