dogfood

Warn

Audited by Snyk on Mar 9, 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.md workflow (Phase 2: Explore) requires navigating to a user-provided target URL and using browser_navigate/browser_snapshot/browser_vision and related tools to read and act on arbitrary public web pages, so the agent will ingest untrusted third-party content that could contain instructions influencing its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 05:54 PM