bearblog

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

• Third-party content exposure detected (high risk: 0.90). The skill's browser workflows (e.g., examples/browser-api-reference.md "Edit Post") navigate to bearblog.dev dashboard pages and use evaluate() to read document.getElementById('body_content').value and header text—i.e., it ingests user-generated blog content from public Bear Blog pages as part of its runtime workflow, which could contain instructions that influence subsequent actions.