seedance-storyboard
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill architecture creates a surface for indirect prompt injection.
- Ingestion points: User input describing the story core, visual style, and action details in SKILL.md (Step 1 and Step 2).
- Boundary markers: Absent; user input is directly concatenated into the prompt templates without delimiters or "ignore embedded instructions" warnings.
- Capability inventory: The skill uses the submit_task tool to execute remote AI generation tasks (consuming user balance) and get_task for result polling.
- Sanitization: No sanitization or validation of user-provided text is performed before it is passed to external model endpoints.
Audit Metadata