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: 1.00). The skill's Phase 3 "Context Gathering" explicitly requires spawning a web-search-researcher Task to research "best practices, common patterns, and pitfalls" on the web and then synthesizes "External Best Practices" from those findings (SKILL.md Phase 3 and Research Findings), meaning it fetches and ingests open/public third‑party content that the agent will interpret and use to make decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 08:32 PM