NYC

linkedin-roast

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill's "Workflow with Claude for Chrome" explicitly grabs a LinkedIn profile tab, takes screenshots, scrolls sections, and calls get_page_text to extract profile text and activity from public LinkedIn pages, meaning it ingests untrusted user-generated third-party content that could carry indirect prompt injections.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:19 PM