normies

Warn

Audited by Snyk on Apr 12, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.90). The Agent Prompt Template and workflow explicitly instruct agents to use browser MCP tools to visit and navigate the provided site URL (e.g., "If browser MCP tools are available, use them to visit the site at [URL]" and "Navigate to [URL]"), which requires fetching and interpreting arbitrary public web content that can be user-generated and could influence the agent's actions and decisions.

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 12, 2026, 07:23 AM
Issues
1