make-vox
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires the installation of standard Python packages, specifically pillow, rembg, and playwright, as well as the installation of chromium browser binaries. These are well-known tools for image processing and web automation.
- [COMMAND_EXECUTION]: The skill executes several local Python and Node.js scripts located in the repo's tools/ and scripts/ directories to handle image generation, cutout processing, web capturing, voice generation, and final rendering.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting untrusted user data to drive the video creation workflow. 1. Ingestion points: User-provided topics in SKILL.md used for project naming and beat sheet generation. 2. Boundary markers: Absent; there are no instructions to the agent to delimit or ignore instructions embedded in the user topic. 3. Capability inventory: The skill has significant capabilities including file system writes and the execution of multiple scripts for content generation. 4. Sanitization: Absent; the skill does not specify any validation or filtering of the user-provided topic before use in the pipeline.
Audit Metadata