skills/kiluazen/kstack/chrome-relay/Gen Agent Trust Hub

chrome-relay

Pass

Audited by Gen Agent Trust Hub on Jul 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill demonstrates a strong security posture by including specific 'Operational guidance' that instructs agents to redact sensitive network headers and avoid echoing secrets in terminal output.\n- [COMMAND_EXECUTION]: The skill uses the chrome-relay CLI tool to perform authorized browser automation tasks such as tab management, page navigation, and element interaction within the user's existing browser session.\n- [EXTERNAL_DOWNLOADS]: Instructions are provided to install the chrome-relay CLI from the well-known NPM registry, which is a standard procedure for this type of developer tooling.\n- [PROMPT_INJECTION]: The skill naturally ingests untrusted content from web pages via DOM snapshots and console logs, which constitutes an inherent surface for indirect prompt injection. This is a standard risk for web-automation skills and is addressed by the author's guidance on handling page data.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 16, 2026, 07:23 PM
Security Audit — agent-trust-hub — chrome-relay