editor-project-export
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests editorial metadata and reference documentation to generate video project files, which represents a surface for indirect prompt injection.
- Ingestion points: The skill reads project data from
05_post/editorial/editor_project.jsonand reference files../../references/EDITOR_PROJECT_EXPORT.mdand../../references/MLT_TOOLKIT.md. - Boundary markers: There are no explicit instructions or delimiters defined to isolate the external data or to instruct the agent to ignore embedded commands.
- Capability inventory: The skill is authorized to run a Python script (
scripts/editor_project_export.py) and interact with MLT services to validate effects. - Sanitization: The instructions do not define any validation or sanitization steps for the data parsed from the manifest before it is passed to the export script.
Audit Metadata