render-creator-pip-listicle
Pass
Audited by Gen Agent Trust Hub on Aug 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes FFmpeg and ffprobe to handle video composition tasks, including cover-scaling creator clips, concatenating beats, and hard-burning overlays.
- [COMMAND_EXECUTION]: Uses Python scripts such as render_product_cards.py and composite_pip.py to generate and composite graphical elements using the Pillow library.
- [EXTERNAL_DOWNLOADS]: Interacts with external AI models from ByteDance (seedream, seedance) via the Fal.ai platform to generate core media assets.
- [DATA_EXFILTRATION]: Facilitates the transfer of media files using presigned URLs, which is standard for cloud-based AI workflows involving temporary asset hosting.
- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface through its processing of configuration data.
- Ingestion points: Configuration fields such as dialogue and descriptor in config.json are used to drive AI generation.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill has the capability to trigger remote AI media generation based on these inputs.
- Sanitization: There is no mention of input validation or sanitization for the text provided in the configuration.
Audit Metadata