creator-production-designer
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the project directory and its outputs are intended for use in a downstream AI production pipeline, creating a surface for indirect prompt injection.
- Ingestion points: The skill reads from
project/screenplay/*,project/continuity/creator-director-vision.md,project/production-design/cinematography/*, andproject/characters/*as specified inSKILL.md. - Boundary markers: Absent. The instructions do not specify the use of delimiters or warnings to ignore embedded instructions within the ingested files.
- Capability inventory: The skill is capable of writing to several files in
project/production-design/*as defined inSKILL.md(e.g.,world-bible.md,location-doc.md,master-reference.md). No network access or subprocess execution capabilities were identified. - Sanitization: Absent. There are no explicit instructions for validating, escaping, or filtering content extracted from external sources.
Audit Metadata