browser-extension-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements a pattern for browser extensions where content scripts ingest data from external web pages and communicate with a background service worker.\n
- Ingestion points: Data is read from the DOM in
content/content-script.jsusingdocument.querySelectorAll.\n - Boundary markers: The provided examples do not include delimiters or instructions to ignore embedded commands within the ingested page content.\n
- Capability inventory: The skill utilizes
chrome.storage.syncfor persistent storage,chrome.runtime.sendMessagefor cross-context messaging, andfetchin the background worker for network operations.\n - Sanitization: No sanitization or validation logic is present for the URLs or data being passed from the untrusted content script context to the privileged background context.
Audit Metadata