higgsfield-motion-design
Pass
Audited by Gen Agent Trust Hub on Jul 4, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any malicious code, hidden instructions, or persistence mechanisms. All logic is focused on the intended creative pipeline.- [PROMPT_INJECTION]: The workflow incorporates user-supplied brand names, taglines, and creative descriptions into prompts for generation models, creating an indirect prompt injection surface. This is a standard and necessary characteristic of AI creative tooling.
- Ingestion points: User answers to brief questions and uploaded media assets (SKILL.md, Step 1 and 2).
- Boundary markers: Absent; user text is interpolated directly into prompt skeletons.
- Capability inventory: Accesses
generate_image,generate_video, and media management tools (SKILL.md). - Sanitization: Absent.- [EXTERNAL_DOWNLOADS]: The skill uses the
media_import_urltool to fetch user-specified remote assets. This is a standard feature for platform media integration and does not involve executing untrusted code.
Audit Metadata