chrome-extension-messaging-tests

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instructional, providing best practices and code snippets for asserting message passing behavior in Chrome extensions. All referenced domains (e.g., example.com) and documentation links (developer.chrome.com) are well-known and safe sources.
  • [INDIRECT_PROMPT_INJECTION]: The skill documentation describes handling data from extension messages, which represents a potential untrusted data ingestion surface.
  • Ingestion points: chrome.runtime.onMessage and chrome.runtime.onMessageExternal listeners used to receive payloads from other extension components or web pages.
  • Boundary markers: The instructions explicitly recommend routing on a message-type field so that exactly one listener owns each type, which serves as a logical boundary.
  • Capability inventory: The snippets include standard capabilities such as network requests (fetch) and native messaging (connectNative).
  • Sanitization: The skill notes that Chrome enforces JSON serialization on these messages, which prevents the transfer of complex executable objects like functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 10:54 AM
Security Audit — agent-trust-hub — chrome-extension-messaging-tests