scenario-wan
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest and process natural language prompts for video generation tasks (Text-to-Video, Image-to-Video, etc.), which are then interpolated into tool parameters.
- Ingestion points: User-provided prompts and video editing instructions are processed as primary inputs for generation jobs (SKILL.md).
- Boundary markers: The instructions do not specify any delimiters or safety markers (such as "ignore embedded instructions" tags) to isolate user-provided prompts from the execution logic.
- Capability inventory: The skill utilizes tools such as
model_run,search, andupload_assetto interact with remote APIs and manage assets (SKILL.md). - Sanitization: No validation, escaping, or filtering of the user-provided prompt content is described prior to its use in tool invocations.
Audit Metadata