linkedin-outreach

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Local Data Storage. All lead data, browser sessions, and action logs are stored in the user's home directory (~/.linkedin-outreach) rather than being transmitted to a remote server.
  • [SAFE]: Manual Authentication. The skill does not handle or automate credential entry; it requires the user to perform the initial login manually in a visible browser window, which prevents credential harvesting and ensures the session is established by the user.
  • [SAFE]: Human-in-the-Loop Validation. The operating rules and script defaults prioritize dry-runs and explicit user approval before performing any outbound actions, such as sending connection requests or messages.
  • [SAFE]: Verified Dependencies. The skill relies on Playwright, a well-known and reputable library for browser automation. Installation and setup instructions use standard package managers and official installation paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 07:22 AM
Security Audit — agent-trust-hub — linkedin-outreach