Masonry: generate images and video with models across providers
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
The agent can use the configured Masonry account to create, check, and download generation jobs, which may consume subscription credits or affect account history.
The skill requires a Masonry credential, which is expected for accessing the Masonry service but gives the CLI access to the user's Masonry account or workspace.
"requires":{"bins":["masonry"],"env":["MASONRY_TOKEN"]} ... primaryEnv":"MASONRY_TOKEN"Use a Masonry token intended for this purpose, preferably scoped to the right workspace if the service supports it, and review generation requests before running them.
Installing or running the CLI executes software from the npm package source on the user's machine.
The skill depends on installing or running an external npm CLI package. That is central to the skill's purpose, but the package code itself is not part of this instruction-only artifact.
npm install -g @masonryai/cli
Install the CLI only from the official package/source you trust, and consider pinning or reviewing the package version in controlled environments.
Prompts, requested media details, and any local reference image used for generation may be processed by Masonry or its model providers.
The skill uses prompts and optionally local image files as inputs to an external generation workflow, which is expected for the purpose but can involve user content leaving the local environment.
Generate AI-powered images and videos from text prompts ... `--image` | `-i` | First frame image (local file)
Avoid using sensitive prompts or private images unless you are comfortable with Masonry's provider and privacy handling for that content.