The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the package @swiftlysingh/excalidraw-cli from the npm registry.
Evidence: The skill documentation states it "fetches @swiftlysingh/excalidraw-cli" and uses npx for installation on the first run.
Source: The package is hosted in a personal namespace and does not belong to a recognized or trusted organization.
[COMMAND_EXECUTION]: The skill executes a shell command to convert Excalidraw files to images.
Evidence: npx @swiftlysingh/excalidraw-cli convert <path>/diagram.excalidraw --format png -o <path>/diagram.png --scale 2.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input to drive a multi-step diagram generation and fixing workflow.
Ingestion points: User-provided ASCII, descriptions, or sketches are passed into the workflow in SKILL.md.
Boundary markers: There are no explicit boundary markers or instructions to ignore embedded commands in the user input.
Capability inventory: The skill can execute shell commands (npx), spawn sub-agents, and write files to the local file system.
Sanitization: No sanitization or validation of the user-provided input is performed before it is passed to the layout planning and sub-agent phases.

excalidraw-render