codebolt-api-access

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

• Third-party content exposure detected (high risk: 0.90). This skill includes browser and crawler modules that navigate to arbitrary public URLs (e.g., codebolt.browser.goToPage + codebolt.browser.getMarkdown/getContent in references/browser.md and codebolt.crawler.goToPage in references/crawler.md), fetch untrusted third-party web page content, and expose that content for the agent to read and act on as part of its workflow.