higgsfield-cinema
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides detailed instructions for filmmaking and sequence generation. All platform interactions, such as cost estimation and workflow lookups via the higgsfield CLI, represent standard usage of the platform's tools for legitimate creative tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through user-provided scene descriptions, @Element tags, and media references (images, video, audio) which are interpolated into model generations. The skill mitigates accidental injection by requiring a strict separation between UI settings and the descriptive prompt body. No instructions to bypass security controls or execute arbitrary code from these inputs were found.
Audit Metadata