flow

Warn

Audited by Snyk on Feb 19, 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 delegates "research requiring web search" (Delegation Decision Tree) and the research workflow (commands/research.md and references/research.md) instructs agents to verify via web search and include URLs/sources, so the agent is expected to fetch and read open/public third‑party content whose instructions could influence planning/execution steps.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 02:41 PM