subagents-orchestration-guide

Warn

Audited by Snyk on Mar 9, 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 skill's Subagents section explicitly marks requirement-analyzer and prd-creator as "WebSearch enabled" (and technical-designer as using "latest technology research") in SKILL.md, meaning the orchestrator will fetch and interpret public web content that can influence scale decisions and downstream autonomous actions, exposing it to indirect prompt injection.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 01:21 AM