subagent-creator

Warn

Audited by Snyk on Feb 15, 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's references/available-tools.md explicitly lists Web Tools (WebFetch, WebSearch) that allow sub-agents to fetch and process open web content, so sub-agents can ingest and read untrusted public/user-generated web pages as part of their workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 09:44 PM