agent-creator

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: 0.80). The skill explicitly directs agents to perform web research and fetch public web content (e.g., "Research Novel Domains
  • Use WebSearch for domain best practices" in Step 0 and "Select Tools: Research: WebSearch, WebFetch, Read" in 2.3), which means the agent will ingest open/public third‑party content that can include untrusted or user-generated material and be read/interpreted as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:29 AM