obsidian-web-clipper

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

• Third-party content exposure detected (high risk: 0.90). The skill's templates explicitly ingest arbitrary webpage content (e.g., {{content}}, {{fullHtml}}, {{selectorHtml}} and URL-based triggers) and send that untrusted page text to the AI interpreter via interpreter prompts (e.g., {{"a summary of the page"}} and the context field), so public third‑party pages can materially influence interpreter outputs and downstream template actions.