cowart-image-gen
Pass
Audited by Gen Agent Trust Hub on Aug 29, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill operates as an instructional set for the agent to use predefined Cowart Model Context Protocol (MCP) tools (e.g.,
get_cowart_selection,insert_cowart_image). These tools reside in the platform environment, not within the skill itself. - [SAFE]: The workflow involves reading and writing canvas state to a local project directory (
projectDir) and managing assets within a structured project folder (canvas/pages/.../assets/). This is standard functionality for the intended use case. - [SAFE]: The skill references an internal
imagegencapability for generating bitmaps and includes logic to resolve local file paths using$CODEX_HOME. This relies on the agent's native environment rather than external remote code execution. - [SAFE]: There are no detected obfuscation techniques, credential exposures, or attempts to bypass safety guidelines. Instructions focus on aspect ratio calculations, tldraw shape metadata, and asset management.
Audit Metadata