reference-video
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from multiple external sources, which creates a potential surface for instructions hidden within processed content.
- Ingestion points: The skill reads data from relative file paths (
../motion-production/references/context.md,../motion-production/references/production.md, and../motion-production/references/native.md) and fetches content via an MCP resource (motion://workflow/production/native). - Boundary markers: There are no defined delimiters or instructions to the agent to disregard potential instructions embedded within these external documents.
- Capability inventory: The skill utilizes the
motion_edit_projecttool to perform write operations on project files based on the ingested context. - Sanitization: The instructions do not specify any validation, filtering, or escaping mechanisms for the content retrieved from external files or resources before processing.
Audit Metadata