The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the moda CLI (e.g., moda brand, moda canvas, moda media) for design workflows and brand management. These tools are authorized via the allowed-tools frontmatter and represent the skill's intended functionality within the agent's environment.
[EXTERNAL_DOWNLOADS]: The skill uses curl to download temporary image previews for visual verification as part of the brand kit auditing process. These downloads target signed, short-lived URLs provided by the Moda platform's internal API, following the vendor's prescribed workflow for asset management.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from external URLs and reads content from existing canvases. It mitigates associated risks through a mandatory evidence chain: Ingestion points include moda brand create --url and moda canvas read; Boundary markers are defined in references/reading-and-verifying.md as a 'data-not-instructions' rule; Capability inventory consists of CLI-based design and file modification tools; Sanitization is achieved via explicit instructions to the agent to treat external content as non-authoritative data.
[DYNAMIC_EXECUTION]: The skill generates and executes sandboxed JavaScript via the moda canvas edit command to perform complex design mutations. These scripts are created at runtime by the agent to perform batch updates and layout adjustments on the canvas.

moda-brand