brainstorm

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's Phase 2 "DIVERGE" workflow explicitly instructs spawning an Explore agent to "Search for SOTA approaches (WebSearch)", which requires fetching and interpreting public web content (untrusted third-party sources) that can influence brainstorming decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 08:46 AM