mushi-integration

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

• Third-party content exposure detected (high risk: 0.90). This workflow’s “Story mapping” stage runs mushi stories map --url https://your-app.com --wait, which (by its purpose) crawls live web pages at runtime (outsider-authored public content) and feeds that scraped page text into the LLM for “Claude drafted user stories.”

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The command "mushi stories map --url https://your-app.com --wait" (https://your-app.com) is fetched at runtime and the crawled page content is used to prompt the AI (Claude) to draft user stories, so the external URL directly influences agent prompts.