The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the excalidraw CLI to perform all drawing and management tasks, requiring the agent to execute multiple shell commands.
[EXTERNAL_DOWNLOADS]: Setup instructions involve installing the excalidraw-cli globally from the author's GitHub repository (github:opencoredev/excalidraw-cli) using the bun package manager.
[DATA_EXFILTRATION]: The excalidraw url command transmits canvas data to the external service excalidraw.com to create encrypted sharing links. This is an intended feature but involves sending user-generated content to a third-party platform.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its processing of untrusted external inputs.
Ingestion points: Reads and processes data from external files via the batch (JSON), mermaid (Mermaid diagrams), and import (.excalidraw files) commands.
Boundary markers: Does not implement delimiters or provide instructions to the agent to ignore potentially malicious instructions embedded within these external files.
Capability inventory: The agent possesses the ability to execute CLI commands, write files to the filesystem (e.g., via --out flags on screenshots and exports), and perform network operations.
Sanitization: There is no evidence of validation or sanitization of the content within the ingested diagram files before they are parsed and rendered.

excalidraw