Storyboard to Video
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-supplied narrative data, such as premises and scripts, to drive powerful generative media tools, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted narrative data enters the agent context through the 'Required inputs' section in
SKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill's instructions.
- Capability inventory: The skill leverages several influential capabilities including
media.generate_video,media.generate_image,media.combine_video, andmedia.upload_file. - Sanitization: There are no documented steps for sanitizing or validating the ingested narrative content before it is interpolated into prompts for the underlying media models.
Audit Metadata