wazza-storyboard
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
ffmpegcommand-line utility to stitch images and audio into a video file. This is a standard media processing operation and is restricted to the local environment. - [DATA_EXFILTRATION]: The skill communicates with
api-pro.wazza.ai, which belongs to the authorwazza-ai. It provides clear instructions on managing API keys through environment variables and warns against exposing them in files or conversations. - [INDIRECT_PROMPT_INJECTION]: Because the skill processes external scripts and API results, it includes a robust safety instruction for the agent to treat all external text as data rather than instructions. This significantly reduces the surface area for indirect prompt injection attacks.
Audit Metadata