runway-upgrade-migration
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill facilitates the use of the official RunwayML SDK for video generation. All provided links point to the service's official documentation and GitHub repositories. No malicious code or unauthorized data access patterns were identified.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-defined text for video generation, which constitutes a potential attack surface for indirect prompt injection.\n
- Ingestion points: The
prompt_textparameter in the Python SDK implementation example inSKILL.md.\n - Boundary markers: None present in the example code snippets.\n
- Capability inventory: The skill utilizes the
runwaymlSDK to interact with external APIs for content generation.\n - Sanitization: The skill does not implement client-side sanitization but notes the existence of the platform's content policy in the error handling section.
Audit Metadata