mfs-find

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow is “search → locate → browse” where mfs search returns hits whose source/locator are then reopened via mfs cat/--range/--locator; if the user’s scope includes outsider-authored content (e.g., web:// crawled pages, github:// issues/PRs, slack:///discord:// messages, zendesk:// ticket comments), that retrieved free text becomes LLM context through the reopened content/snippets.