obsidian-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly exposes the agent to arbitrary public web pages via the "obsidian web url="..."" command in SKILL.md and provides DOM-querying commands (e.g., "obsidian dev:dom ... text/inner") that let the agent read and act on page content, enabling untrusted third-party content to influence behavior.