obsidian-excalidraw

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Outsider-authored free text can be ingested at runtime because scripts/to-obsidian-md.js and scripts/write-to-vault.js read a JSON document from stdin/files (JSON.parse of arbitrary doc/doc.elements[].text) and then embed those text strings into the generated Obsidian note content.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 1.00). The skill explicitly tells the user to "Run it unsandboxed (the CLI hangs under the sandbox)" and to use the Obsidian CLI to write into user vault paths, which is an instruction to bypass sandboxing/security protections and thus can compromise the machine state.