create-subagents

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: 0.90). This skill explicitly allows subagents to use WebSearch/WebFetch and includes examples like "Attempt to fetch latest API documentation from web" (references/subagents.md and references/error-handling-and-recovery.md), meaning agents can fetch and interpret arbitrary public web/third-party content which is untrusted and user-generated.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:39 PM