Browser

Warn

Audited by Snyk on Feb 16, 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 explicitly navigates to and ingests arbitrary public URLs via the CLI and API (e.g., "bun run $PAI_DIR/skills/Browser/Tools/Browse.ts screenshot ", navigate(), getVisibleHtml(), getVisibleText(), and Workflows/Extract.md), so the agent will fetch and read untrusted third-party web content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 12:55 AM