alterlab-genai-image-to-video
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill demonstrates an indirect prompt injection surface through its standard workflow.
- Ingestion points: The agent is instructed to 'search the web for current Soul ID capabilities' and 'read existing project files (storyboards, shot lists, image asset inventories)' to gather context for the production pipeline.
- Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions to isolate ingested data from the agent's core mission logic.
- Capability inventory: The agent has permissions to perform web searches and write structured production guides to the local file system (e.g., '{project}-shot-plan.md').
- Sanitization: There are no requirements for validating, escaping, or filtering content retrieved from external sources or project files before it is processed or written to new deliverables.
Audit Metadata