alterlab-genai-motion-designer
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions define an autonomous production workflow that processes external inputs, establishing a vulnerability to indirect prompt injection.
- Ingestion points: The agent is directed to read external project files including briefs, brand guidelines, and asset inventories.
- Capability inventory: The agent is empowered to perform web searches and write multiple structured output files to the local filesystem.
- Boundary markers: There are no instructions to use delimiters or to disregard potential commands found within the ingested data.
- Sanitization: The skill lacks any requirement to sanitize or validate the external content before it is integrated into the agent's decision-making or output generation process.
Audit Metadata