every-format-from-one-edit
Pass
Audited by Gen Agent Trust Hub on Nov 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill implements a legitimate workflow for video editing, including aspect ratio derivation and rendering, using tools associated with the vendor infrastructure (e.g.,
derive_composition,create_render). - [INDIRECT_PROMPT_INJECTION]: The skill processes external video composition data which could potentially contain untrusted instructions.
- Ingestion points: Master composition data and metadata retrieved via
list_compositionsin SKILL.md. - Boundary markers: Absent; the instructions do not specify delimiters for separating untrusted project data from instructions.
- Capability inventory: Includes
derive_composition,apply_composition, andcreate_renderin SKILL.md. - Sanitization: No specific content validation or sanitization of ingested composition data is described.
Audit Metadata