brainstorm

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 explicitly instructs the agent to use WebSearch, WebFetch, and the context7 MCP to fetch documentation, blog posts, and other web resources during Phase 3 ("Tools during brainstorming"), which means it will ingest open/public third-party content that can influence decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 03:07 AM