kling-studio
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text prompts and external media URLs (images and videos) as part of its video generation workflow. This establishes a surface for indirect prompt injection, where malicious instructions could be embedded in the processed data.
- Ingestion points: User-provided prompts and external resource URLs (images/videos) processed by the workflow described in
SKILL.md. - Boundary markers: None; the instructions do not implement delimiters or explicit warnings to ignore instructions embedded within user input.
- Capability inventory: Network operations (HTTP POST/GET requests) to the Kling AI API endpoints as implemented in
scripts/kling_api.py. - Sanitization: None; input data is passed to the API request payload without explicit escaping or validation.
- [EXTERNAL_DOWNLOADS]: The skill documentation and setup instructions specify dependencies on the
PyJWTandrequestsPython libraries, which are standard packages used for generating authentication tokens and facilitating API communication.
Audit Metadata