agent-builder

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: 0.90). This skill explicitly lists and configures web-facing tools like WebFetch and WebSearch (see the "Tool configuration patterns" and agents such as security-auditor and data-scientist which include WebSearch/WebFetch), so the agent can fetch and read open/public web content that is untrusted and user-generated.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:02 PM