scenario-veo
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation and examples for using video generation tools through a verified vendor. It references sibling skills authored by scenario-labs and provides a secure mechanism for managing missing dependencies by instructing the agent to prompt the user for installation rather than executing commands directly.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a functional surface for processing untrusted user input via video generation prompts. Evidence: The prompt parameter in model_run calls (SKILL.md). Boundary markers and sanitization are not explicitly defined in the instructions, which is consistent with the primary use case of a generative text-to-video interface.
Audit Metadata